Showing 1–31 of 31 results for author: Ahuja, S

Smartphone Audio Based Distress Detection

Authors: Anil Sharma, Sarthak Ahuja, Mayank Gautam, Sanjit Kaul

Abstract: We investigate an unobtrusive and $24\times7$ human distress detection and signaling system, Always Alert, that requires the smartphone, and not its human owner, to be on alert. The system leverages the microphone sensor, at least one of which is available on every phone, and assumes the availability of a data network. We propose a novel two-stage supervised learning framework, using support vecto… ▽ More We investigate an unobtrusive and $24\times7$ human distress detection and signaling system, Always Alert, that requires the smartphone, and not its human owner, to be on alert. The system leverages the microphone sensor, at least one of which is available on every phone, and assumes the availability of a data network. We propose a novel two-stage supervised learning framework, using support vector machines (SVMs), that executes on a user's smartphone and monitors natural vocal expressions of fear---screaming and crying in our study---when a human being is in harm's way. The challenge is to achieve a high distress detection rate while ensuring that the false alarm rate is a manageable overhead, while a typical smartphone user goes about living life as usual. We train the learning framework with carefully selected audio fingerprints of distress and of varied environmental contexts. The audio is used to tune the learning framework to obtain a desirable distress detection rate and false alarm rate (FAR). The ability of the proposed framework to detect distress in rather challenging audio environments is demonstrated. Exploiting the time contiguous nature of false alarms further allows us to reduce the FAR. We show the feasibility of using our framework anytime and anywhere by testing it over many hours of audio fingerprints recorded by volunteers on their smartphones, as they went about their daily routines. We are able to achieve high distress detection rates at an average overhead that is equivalent to about 1 facebook post every 3 to 4 hours. △ Less

Submitted 4 August, 2026; originally announced August 2026.

SEGRA: Structured Experience-Guided Graph Reasoning Agent for Gremlin Based Question Answering

Authors: Saiyue Lyu, Mariam Dundua, Vishaal Kapoor, Sarthak Ahuja, Neda Kordjazi, Evren Yortucboylu, Harsh Amin, Rebecca Steinert

Abstract: Enterprise IT support knowledge graphs capture rich relationships among cases, users, devices, symptoms, taxonomic categories, root causes, and historical resolutions. Yet querying them in Gremlin requires knowledge of graph schemas, traversal semantics, edge directionality, and property-graph-specific constraints, making them difficult for non-expert operators to use. We introduce SEGRA, an exper… ▽ More Enterprise IT support knowledge graphs capture rich relationships among cases, users, devices, symptoms, taxonomic categories, root causes, and historical resolutions. Yet querying them in Gremlin requires knowledge of graph schemas, traversal semantics, edge directionality, and property-graph-specific constraints, making them difficult for non-expert operators to use. We introduce SEGRA, an experience-guided agent for enterprise text-to-Gremlin question answering. SEGRA integrates intent routing, schema- and taxonomy-grounded query generation, multi-shot decomposition, execution-aware verification, and a curriculum-bootstrapped skill library that reuses verified query patterns. On an enterprise IT support benchmark, SEGRA achieves a $7.0\times$ higher mean judge score than backbone-only chain-of-thought prompting. Its skill library further reduces LLM calls by $20\%$ and dollar cost by $18\%$ relative to SEGRA without skills, while preserving answer quality. These results show that schema-grounded agent design and reusable execution experience improve both accuracy and efficiency for enterprise graph QA. △ Less

Submitted 20 July, 2026; originally announced July 2026.

Every Eval Ever: A Unifying Schema and Community Repository for AI Evaluation Results

Authors: Jan Batzner, Sree Harsha Nelaturu, Damian Stachura, Anastassia Kornilova, Jon Crall, Tommaso Cerruti, Yanan Long, Yifan Mai, Sanchit Ahuja, Asaf Yehudai, Marek Šuppa, John P. Lalor, Oluwagbemike Olowe, Jatin Ganhotra, Brian H. Hu, Eliya Habba, Andrew M. Bean, Chang Liu, Sander Land, Steven Dillmann, Aniketh Garikaparthi, Elron Bandel, Saki Imai, James Edgell, Wm. Matthew Kennedy , et al. (23 additional authors not shown)

Abstract: AI evaluations are widely used for testing and understanding progress. However, the diverse evaluators bring with them inconsistencies that challenge analysis and comparison. First, results are saved in incompatible formats, scattered across leaderboards, papers, blog posts, evaluation harness logs, and custom repositories. Second, results are created by different evaluation frameworks, which prod… ▽ More AI evaluations are widely used for testing and understanding progress. However, the diverse evaluators bring with them inconsistencies that challenge analysis and comparison. First, results are saved in incompatible formats, scattered across leaderboards, papers, blog posts, evaluation harness logs, and custom repositories. Second, results are created by different evaluation frameworks, which produce divergent scores for nominally identical evaluations and record metadata inconsistently, hindering comparison, cross-community evaluation science, cost reduction, and reuse. We introduce Every Eval Ever, the first shared schema and community-crowdsourced repository for AI evaluation results. The schema standardizes how evaluations are represented in a unified, single JSON document. It is source-agnostic by design, ingesting results from evaluation harnesses and papers alike, and optionally stores per-instance outputs for fine-grained analysis. We contribute: (i) a community-governed metadata schema with a companion instance-level schema, the first standardization effort of its kind; (ii) automatic converters from popular formats, evaluation harnesses, and leaderboards to the unified schema; and (iii) a crowdsourced community database hosted on Hugging Face, currently spanning to date 22,235 models, 2,273 unique benchmarks, and 31 evaluation formats. △ Less

Submitted 12 June, 2026; originally announced June 2026.

Parameter Alignment Mitigates Catastrophic Forgetting in Multilingual Expert Language Models

Authors: Sanchit Ahuja, Terra Blevins

Abstract: While continual pretraining~(CPT) is a practical way to extend large language models to new languages, naïve finetuning on targeted data erodes existing capabilities through catastrophic forgetting. Organizing training around language families reduces cross-language interference but cannot alone prevent forgetting of the general knowledge needed for downstream tasks. We link this forgetting to par… ▽ More While continual pretraining~(CPT) is a practical way to extend large language models to new languages, naïve finetuning on targeted data erodes existing capabilities through catastrophic forgetting. Organizing training around language families reduces cross-language interference but cannot alone prevent forgetting of the general knowledge needed for downstream tasks. We link this forgetting to parameter drift in multilingual CPT and present a suite of five layer-aware parameter alignment strategies: hard layer freezing, soft regularization, post-hoc weight reversion, and model merging. We systematically compare our alignment strategies against two unregularized CPT baselines on benchmarks spanning 32 training languages from five language families, plus held-out languages, across four evaluation axes: perplexity, reading comprehension, physical reasoning, and translation. Parameter alignment substantially reduces forgetting at minimal cost to language acquisition: layer freezing and regularization best preserve comprehension, whereas post-hoc reversion yields the strongest translation gains. Together, these results map the acquisition--forgetting frontier for family-expert CPT and offer practical deployment guidelines pairing each strategy to the tasks it best serves. △ Less

Submitted 29 May, 2026; originally announced June 2026.

Comments: 25 Pages, 5 Figures

Quieting the Cobwebs: Browser Interaction for Visual Floaters

Authors: Kenneth Ge, Jinglin Li, Shikhar Ahuja

Abstract: Floaters, cobweb-like shadows that move around a person's visual field, impair vision for nearly 33% of the population, yet have limited treatment options. Floaters especially harm screen use, since they reduce contrast, introduce clutter, and add moving distractions. While existing high-contrast tools offer some help, few address the motion that makes screen use with floaters uniquely difficult.… ▽ More Floaters, cobweb-like shadows that move around a person's visual field, impair vision for nearly 33% of the population, yet have limited treatment options. Floaters especially harm screen use, since they reduce contrast, introduce clutter, and add moving distractions. While existing high-contrast tools offer some help, few address the motion that makes screen use with floaters uniquely difficult. In this paper, we build a floater simulation inspired by the physics of the eye, use it to quantitatively assess text readability at varying levels of motion, and build a novel web extension that minimizes eye movement, maximizing the signal-to-noise ratio of performing browser tasks. Importantly, our tool works not only for text, but for all UI elements, requiring no modifications to existing websites. △ Less

Submitted 16 August, 2026; v1 submitted 12 May, 2026; originally announced May 2026.

Comments: Accepted at ECCV 2026 HCV Workshop

DQA: Diagnostic Question Answering for IT Support

Authors: Vishaal Kapoor, Mariam Dundua, Sarthak Ahuja, Neda Kordjazi, Evren Yortucboylu, Vaibhavi Padala, Derek Ho, Jennifer Whitted, Rebecca Steinert

Abstract: Enterprise IT support interactions are fundamentally diagnostic: effective resolution requires iterative evidence gathering from ambiguous user reports to identify an underlying root cause. While retrieval-augmented generation (RAG) provides grounding through historical cases, standard multi-turn RAG systems lack explicit diagnostic state and therefore struggle to accumulate evidence and resolve c… ▽ More Enterprise IT support interactions are fundamentally diagnostic: effective resolution requires iterative evidence gathering from ambiguous user reports to identify an underlying root cause. While retrieval-augmented generation (RAG) provides grounding through historical cases, standard multi-turn RAG systems lack explicit diagnostic state and therefore struggle to accumulate evidence and resolve competing hypotheses across turns. We introduce DQA, a diagnostic question-answering framework that maintains persistent diagnostic state and aggregates retrieved cases at the level of root causes rather than individual documents. DQA combines conversational query rewriting, retrieval aggregation, and state-conditioned response generation to support systematic troubleshooting under enterprise latency and context constraints. We evaluate DQA on 150 anonymized enterprise IT support scenarios using a replay-based protocol. Averaged over three independent runs, DQA achieves a 78.7% success rate under a trajectory-level success criterion, compared to 41.3% for a multi-turn RAG baseline, while reducing average turns from 8.4 to 3.9. △ Less

Submitted 8 April, 2026; v1 submitted 6 April, 2026; originally announced April 2026.

Comments: 7 pages, 2 tables, submitted at ACL 2026 Industry Track

ACM Class: I.2.7

VIGIL: Towards Edge-Extended Agentic AI for Enterprise IT Support

Authors: Sarthak Ahuja, Neda Kordjazi, Evren Yortucboylu, Vishaal Kapoor, Mariam Dundua, Yiming Li, Derek Ho, Vaibhavi Padala, Jennifer Whitted, Rebecca Steinert

Abstract: Enterprise IT support is constrained by heterogeneous devices, evolving policies, and long-tail failure modes that are difficult to resolve centrally. We present VIGIL, an edge-extended agentic AI system that deploys desktop-resident agents to perform situated diagnosis, retrieval over enterprise knowledge, and policy-governed remediation directly on user devices with explicit consent and end-to-e… ▽ More Enterprise IT support is constrained by heterogeneous devices, evolving policies, and long-tail failure modes that are difficult to resolve centrally. We present VIGIL, an edge-extended agentic AI system that deploys desktop-resident agents to perform situated diagnosis, retrieval over enterprise knowledge, and policy-governed remediation directly on user devices with explicit consent and end-to-end observability. In a 10-week pilot of VIGIL's operational loop on 100 resource-constrained endpoints, VIGIL reduces interaction rounds by 39%, achieves at least 4 times faster diagnosis, and supports self-service resolution in 82% of matched cases. Users report excellent usability, high trust, and low cognitive workload across four validated instruments, with qualitative feedback highlighting transparency as critical for trust. Notably, users rated the system higher when no historical matches were available, suggesting on-device diagnosis provides value independent of knowledge base coverage. This pilot establishes safety and observability foundations for fleet-wide continuous improvement. △ Less

Submitted 17 March, 2026; originally announced March 2026.

Adversarial Latent-State Training for Robust Policies in Partially Observable Domains

Authors: Angad Singh Ahuja

Abstract: Robustness under latent distribution shift remains challenging in partially observable reinforcement learning. We formalize a focused setting where an adversary selects a hidden initial latent distribution before the episode, termed an adversarial latent-initial-state POMDP. Theoretically, we prove a latent minimax principle, characterize worst-case defender distributions, and derive approximate b… ▽ More Robustness under latent distribution shift remains challenging in partially observable reinforcement learning. We formalize a focused setting where an adversary selects a hidden initial latent distribution before the episode, termed an adversarial latent-initial-state POMDP. Theoretically, we prove a latent minimax principle, characterize worst-case defender distributions, and derive approximate best-response inequalities with finite-sample concentration bounds that make the optimization and sampling terms explicit. Empirically, using a Battleship benchmark, we demonstrate that targeted exposure to shifted latent distributions reduces average robustness gaps between Spread and Uniform distributions from 10.3 to 3.1 shots at equal budget. Furthermore, iterative best-response training exhibits budget-sensitive behavior that is qualitatively consistent with the theorem-guided diagnostics once one accounts for discounted PPO surrogates and finite-sample noise. Ultimately, we show that for latent-initial-state problems, the framework yields a clean evaluation game and useful theorem-motivated diagnostics while also making clear where implementation-level surrogates and optimization limits enter. △ Less

Submitted 8 August, 2026; v1 submitted 7 March, 2026; originally announced March 2026.

Comments: Contrary results found

When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation

Authors: Mubashara Akhtar, Anka Reuel, Prajna Soni, Sanchit Ahuja, Pawan Sasanka Ammanamanchi, Ruchit Rawal, Vilém Zouhar, Srishti Yadav, Chenxi Whitehouse, Dayeon Ki, Jennifer Mickel, Leshem Choshen, Marek Šuppa, Jan Batzner, Jenny Chim, Jeba Sania, Yanan Long, Hossein A. Rahmani, Christina Knight, Yiyang Nan, Jyoutir Raj, Yu Fan, Shubham Singh, Subramanyam Sahoo, Eliya Habba , et al. (12 additional authors not shown)

Abstract: Artificial intelligence benchmarks are an important mechanism to measure model progress and guide deployment decisions. However, benchmarks quickly "saturate", making it difficult to differentiate models and diminishing their long-term value. In this study, we define benchmark saturation and analyze it across 60 language model benchmarks using 14 properties that relate to saturation. We find that… ▽ More Artificial intelligence benchmarks are an important mechanism to measure model progress and guide deployment decisions. However, benchmarks quickly "saturate", making it difficult to differentiate models and diminishing their long-term value. In this study, we define benchmark saturation and analyze it across 60 language model benchmarks using 14 properties that relate to saturation. We find that nearly half of our benchmarks exhibit saturation, with rates increasing with age. Further, we find that resilience to saturation is impacted by expert-curation, not by public test data. Our results suggest that design choices can extend benchmark longevity and inform more durable evaluation approaches. △ Less

Submitted 6 August, 2026; v1 submitted 18 February, 2026; originally announced February 2026.

Comments: Published at ICML 2026 (Forty-Third International Conference on Machine Learning)

Inference-Time Loss-Guided Colour Preservation in Diffusion Sampling

Authors: Angad Singh Ahuja, Aarush Ram Anandh

Abstract: Precise color control remains a persistent failure mode in text-to-image diffusion systems, particularly in design-oriented workflows where outputs must satisfy explicit, user-specified color targets. We present an inference-time, region-constrained color preservation method that steers a pretrained diffusion model without any additional training. Our approach combines (i) ROI-based inpainting for… ▽ More Precise color control remains a persistent failure mode in text-to-image diffusion systems, particularly in design-oriented workflows where outputs must satisfy explicit, user-specified color targets. We present an inference-time, region-constrained color preservation method that steers a pretrained diffusion model without any additional training. Our approach combines (i) ROI-based inpainting for spatial selectivity, (ii) background-latent re-imposition to prevent color drift outside the ROI, and (iii) latent nudging via gradient guidance using a composite loss defined in CIE Lab and linear RGB. The loss is constructed to control not only the mean ROI color but also the tail of the pixelwise error distribution through CVaR-style and soft-maximum penalties, with a late-start gate and a time-dependent schedule to stabilize guidance across denoising steps. We show that mean-only baselines can satisfy average color constraints while producing perceptually salient local failures, motivating our distribution-aware objective. The resulting method provides a practical, training-free mechanism for targeted color adherence that can be integrated into standard Stable Diffusion inpainting pipelines. △ Less

Submitted 23 January, 2026; originally announced January 2026.

Comments: 25 Pages, 12 Figures, 3 Tables, 5 Appendices, 8 Algorithms

MSC Class: I.4; I.5; I.3; B.8

OpenProposal Platform for Transparent Research Funding Review

Authors: Sakshi Ahuja, Subhankar Mishra

Abstract: Research funding allocation remains a critical bottleneck in scientific advancement, yet the review process for funding proposals lacks the transparency that has revolutionized academic paper peer review. Traditional funding agencies operate with closed review systems, limiting accountability and preventing systematic improvements. We present OpenProposal, a proof-of-concept web-based platform tha… ▽ More Research funding allocation remains a critical bottleneck in scientific advancement, yet the review process for funding proposals lacks the transparency that has revolutionized academic paper peer review. Traditional funding agencies operate with closed review systems, limiting accountability and preventing systematic improvements. We present OpenProposal, a proof-of-concept web-based platform that explores how transparency principles from OpenReview might be adapted to research funding proposal evaluation. Built using modern web technologies including Next.js , React , and Prisma , OpenProposal demonstrates the technical feasibility of public reviews, author rebuttals, and transparent decision-making while attempting to protect sensitive information such as budgets. Our platform prototype addresses key limitations identified in current funding systems by providing mechanisms for community engagement, reviewer accountability, and potential data-driven insights into peer review processes. Through system design and implementation, we explore how transparent funding review could potentially enhance scientific integrity and improve research funding decisions, though empirical validation remains necessary. This work contributes a technical foundation for transparent funding review and identifies design considerations for future research on peer review mechanisms in funding contexts. △ Less

Submitted 15 December, 2025; originally announced December 2025.

Meta-Learning for Cross-Task Generalization in Protein Mutation Property Prediction

Authors: Srivathsan Badrinarayanan, Yue Su, Janghoon Ock, Alan Pham, Sanya Ahuja, Amir Barati Farimani

Abstract: Protein mutations can have profound effects on biological function, making accurate prediction of property changes critical for drug discovery, protein engineering, and precision medicine. Current approaches rely on fine-tuning protein-specific transformers for individual datasets, but struggle with cross-dataset generalization due to heterogeneous experimental conditions and limited target domain… ▽ More Protein mutations can have profound effects on biological function, making accurate prediction of property changes critical for drug discovery, protein engineering, and precision medicine. Current approaches rely on fine-tuning protein-specific transformers for individual datasets, but struggle with cross-dataset generalization due to heterogeneous experimental conditions and limited target domain data. We introduce two key innovations: (1) the first application of Model-Agnostic Meta-Learning (MAML) to protein mutation property prediction, and (2) a novel mutation encoding strategy using separator tokens to directly incorporate mutations into sequence context. We build upon transformer architectures integrating them with MAML to enable rapid adaptation to new tasks through minimal gradient steps rather than learning dataset-specific patterns. Our mutation encoding addresses the critical limitation where standard transformers treat mutation positions as unknown tokens, significantly degrading performance. Evaluation across three diverse protein mutation datasets (functional fitness, thermal stability, and solubility) demonstrates significant advantages over traditional fine-tuning. In cross-task evaluation, our meta-learning approach achieves 29% better accuracy for functional fitness with 65% less training time, and 94% better accuracy for solubility with 55% faster training. The framework maintains consistent training efficiency regardless of dataset size, making it particularly valuable for industrial applications and early-stage protein design where experimental data is limited. This work establishes a systematic application of meta-learning to protein mutation analysis and introduces an effective mutation encoding strategy, offering transformative methodology for cross-domain generalization in protein engineering. △ Less

Submitted 23 October, 2025; originally announced October 2025.

UPDESH: Synthesizing Grounded Instruction Tuning Data for 13 Indic Languages

Authors: Pranjal A. Chitale, Varun Gumma, Sanchit Ahuja, Prashant Kodali, Manan Uppadhyay, Deepthi Sudharsan, Sunayana Sitaram

Abstract: Developing culturally grounded multilingual AI systems remains challenging, particularly for low-resource languages. While synthetic data offers promise, its effectiveness in multilingual and multicultural contexts is underexplored. We investigate bottom-up synthetic data generation using large open-source LLMs (>= 235B parameters) grounded in language-specific Wikipedia content, complementing dom… ▽ More Developing culturally grounded multilingual AI systems remains challenging, particularly for low-resource languages. While synthetic data offers promise, its effectiveness in multilingual and multicultural contexts is underexplored. We investigate bottom-up synthetic data generation using large open-source LLMs (>= 235B parameters) grounded in language-specific Wikipedia content, complementing dominant top-down translation-based approaches from English. We introduce Updesh, a high-quality large-scale synthetic instruction-following dataset comprising 9.5M data points across 13 Indian languages and English, encompassing diverse reasoning and generative tasks. Comprehensive evaluation using automated metrics and 10K human assessments confirms high data quality. Downstream evaluations performed by fine-tuning models on various datasets and assessing performance across 13 diverse multilingual datasets and model comparative evaluations, demonstrate that models trained on Updesh consistently obtain significant improvements on NLU, NLG evaluations. Finally, through ablation studies and cultural evaluations, we show that context-aware, culturally grounded data generation is essential for effective multilingual AI development. △ Less

Submitted 26 February, 2026; v1 submitted 25 September, 2025; originally announced September 2025.

Comments: Under Review

EfficientXLang: Towards Improving Token Efficiency Through Cross-Lingual Reasoning

Authors: Sanchit Ahuja, Praneetha Vaddamanu, Barun Patra

Abstract: Despite recent advances in Language Reasoning Models (LRMs), most research focuses solely on English, even though many models are pretrained on multilingual data. In this work, we investigate: Is English the most token-efficient language for reasoning? We evaluate three open-source RLMs: DeepSeek R1, Qwen 2.5 and Qwen 3, across four math datasets and seven typologically diverse languages. We find… ▽ More Despite recent advances in Language Reasoning Models (LRMs), most research focuses solely on English, even though many models are pretrained on multilingual data. In this work, we investigate: Is English the most token-efficient language for reasoning? We evaluate three open-source RLMs: DeepSeek R1, Qwen 2.5 and Qwen 3, across four math datasets and seven typologically diverse languages. We find that reasoning in non-English languages not only reduces token usage, but also preserves accuracy. These gains persist even after translating the reasoning traces into English, suggesting genuine shifts in reasoning behavior rather than surface-level linguistic effects. The extent of improvement, however, depends on the models multilingual strength. Our findings motivate a broader view of reasoning in language models, highlighting the potential of multilingual reasoning and the importance of strong multilingual foundations. The code for our work can be found: https://github.com/microsoft/EfficientXLang. △ Less

Submitted 30 June, 2025; originally announced July 2025.

Comments: 15 pages, 5 figures, 9 tables

Improving Tool Retrieval by Leveraging Large Language Models for Query Generation

Authors: Mohammad Kachuee, Sarthak Ahuja, Vaibhav Kumar, Puyang Xu, Xiaohu Liu

Abstract: Using tools by Large Language Models (LLMs) is a promising avenue to extend their reach beyond language or conversational settings. The number of tools can scale to thousands as they enable accessing sensory information, fetching updated factual knowledge, or taking actions in the real world. In such settings, in-context learning by providing a short list of relevant tools in the prompt is a viabl… ▽ More Using tools by Large Language Models (LLMs) is a promising avenue to extend their reach beyond language or conversational settings. The number of tools can scale to thousands as they enable accessing sensory information, fetching updated factual knowledge, or taking actions in the real world. In such settings, in-context learning by providing a short list of relevant tools in the prompt is a viable approach. To retrieve relevant tools, various approaches have been suggested, ranging from simple frequency-based matching to dense embedding-based semantic retrieval. However, such approaches lack the contextual and common-sense understanding required to retrieve the right tools for complex user requests. Rather than increasing the complexity of the retrieval component itself, we propose leveraging LLM understanding to generate a retrieval query. Then, the generated query is embedded and used to find the most relevant tools via a nearest-neighbor search. We investigate three approaches for query generation: zero-shot prompting, supervised fine-tuning on tool descriptions, and alignment learning by iteratively optimizing a reward metric measuring retrieval performance. By conducting extensive experiments on a dataset covering complex and multi-tool scenarios, we show that leveraging LLMs for query generation improves the retrieval for in-domain (seen tools) and out-of-domain (unseen tools) settings. △ Less

Submitted 16 November, 2024; originally announced December 2024.

Journal ref: COLING 2025

Contamination Report for Multilingual Benchmarks

Authors: Sanchit Ahuja, Varun Gumma, Sunayana Sitaram

Abstract: Benchmark contamination refers to the presence of test datasets in Large Language Model (LLM) pre-training or post-training data. Contamination can lead to inflated scores on benchmarks, compromising evaluation results and making it difficult to determine the capabilities of models. In this work, we study the contamination of popular multilingual benchmarks in LLMs that support multiple languages.… ▽ More Benchmark contamination refers to the presence of test datasets in Large Language Model (LLM) pre-training or post-training data. Contamination can lead to inflated scores on benchmarks, compromising evaluation results and making it difficult to determine the capabilities of models. In this work, we study the contamination of popular multilingual benchmarks in LLMs that support multiple languages. We use the Black Box test to determine whether $7$ frequently used multilingual benchmarks are contaminated in $7$ popular open and closed LLMs and find that almost all models show signs of being contaminated with almost all the benchmarks we test. Our findings can help the community determine the best set of benchmarks to use for multilingual evaluation. △ Less

Submitted 21 October, 2024; originally announced October 2024.

Comments: 11 pages, 2 tables

Scaling Laws for Multilingual Language Models

Authors: Yifei He, Alon Benhaim, Barun Patra, Praneetha Vaddamanu, Sanchit Ahuja, Parul Chopra, Vishrav Chaudhary, Han Zhao, Xia Song

Abstract: We propose a novel scaling law for general-purpose decoder-only language models (LMs) trained on multilingual data, tackling the problem of balancing languages during multilingual pretraining. A primary challenge in studying multilingual scaling is the difficulty of analyzing individual language performance due to cross-lingual transfer. To address this, we shift the focus from individual language… ▽ More We propose a novel scaling law for general-purpose decoder-only language models (LMs) trained on multilingual data, tackling the problem of balancing languages during multilingual pretraining. A primary challenge in studying multilingual scaling is the difficulty of analyzing individual language performance due to cross-lingual transfer. To address this, we shift the focus from individual languages to language families. We introduce and validate a hypothesis that the test cross-entropy loss for each language family is determined solely by its own sampling ratio, independent of other languages in the mixture. This insight simplifies the complexity of multilingual scaling and make the analysis scalable to an arbitrary number of languages. Building on this hypothesis, we derive a power-law relationship that links performance with dataset size, model size and sampling ratios. This relationship enables us to predict performance across various combinations of the above three quantities, and derive the optimal sampling ratios at different model scales. To demonstrate the effectiveness and accuracy of our proposed scaling law, we perform a large-scale empirical study, training more than 100 models on 23 languages spanning 5 language families. Our experiments show that the optimal sampling ratios derived from small models (85M parameters) generalize effectively to models that are several orders of magnitude larger (1.2B parameters), offering a resource-efficient approach for multilingual LM training at scale. △ Less

Submitted 3 December, 2024; v1 submitted 15 October, 2024; originally announced October 2024.

sPhinX: Sample Efficient Multilingual Instruction Fine-Tuning Through N-shot Guided Prompting

Authors: Sanchit Ahuja, Kumar Tanmay, Hardik Hansrajbhai Chauhan, Barun Patra, Kriti Aggarwal, Luciano Del Corro, Arindam Mitra, Tejas Indulal Dhamecha, Ahmed Awadallah, Monojit Choudhary, Vishrav Chaudhary, Sunayana Sitaram

Abstract: Despite the remarkable success of large language models (LLMs) in English, a significant performance gap remains in non-English languages. To address this, we introduce a novel approach for strategically constructing a multilingual synthetic instruction tuning dataset, sPhinX. Unlike prior methods that directly translate fixed instruction-response pairs, sPhinX enhances diversity by selectively au… ▽ More Despite the remarkable success of large language models (LLMs) in English, a significant performance gap remains in non-English languages. To address this, we introduce a novel approach for strategically constructing a multilingual synthetic instruction tuning dataset, sPhinX. Unlike prior methods that directly translate fixed instruction-response pairs, sPhinX enhances diversity by selectively augmenting English instruction-response pairs with multilingual translations. Additionally, we propose LANGIT, a novel N-shot guided fine-tuning strategy, which further enhances model performance by incorporating contextually relevant examples in each training sample. Our ablation study shows that our approach enhances the multilingual capabilities of Mistral-7B and Phi-3-Small improving performance by an average of 39.8% and 11.2%, respectively, across multilingual benchmarks in reasoning, question answering, reading comprehension, and machine translation. Moreover, sPhinX maintains strong performance on English LLM benchmarks while exhibiting minimal to no catastrophic forgetting, even when trained on 51 languages. △ Less

Submitted 18 June, 2025; v1 submitted 13 July, 2024; originally announced July 2024.

Comments: 20 pages, 12 tables, 5 figures

SemEval-2024 Task 1: Semantic Textual Relatedness for African and Asian Languages

Authors: Nedjma Ousidhoum, Shamsuddeen Hassan Muhammad, Mohamed Abdalla, Idris Abdulmumin, Ibrahim Said Ahmad, Sanchit Ahuja, Alham Fikri Aji, Vladimir Araujo, Meriem Beloucif, Christine De Kock, Oumaima Hourrane, Manish Shrivastava, Thamar Solorio, Nirmal Surange, Krishnapriya Vishnubhotla, Seid Muhie Yimam, Saif M. Mohammad

Abstract: We present the first shared task on Semantic Textual Relatedness (STR). While earlier shared tasks primarily focused on semantic similarity, we instead investigate the broader phenomenon of semantic relatedness across 14 languages: Afrikaans, Algerian Arabic, Amharic, English, Hausa, Hindi, Indonesian, Kinyarwanda, Marathi, Moroccan Arabic, Modern Standard Arabic, Punjabi, Spanish, and Telugu. The… ▽ More We present the first shared task on Semantic Textual Relatedness (STR). While earlier shared tasks primarily focused on semantic similarity, we instead investigate the broader phenomenon of semantic relatedness across 14 languages: Afrikaans, Algerian Arabic, Amharic, English, Hausa, Hindi, Indonesian, Kinyarwanda, Marathi, Moroccan Arabic, Modern Standard Arabic, Punjabi, Spanish, and Telugu. These languages originate from five distinct language families and are predominantly spoken in Africa and Asia -- regions characterised by the relatively limited availability of NLP resources. Each instance in the datasets is a sentence pair associated with a score that represents the degree of semantic textual relatedness between the two sentences. Participating systems were asked to rank sentence pairs by their closeness in meaning (i.e., their degree of semantic relatedness) in the 14 languages in three main tracks: (a) supervised, (b) unsupervised, and (c) crosslingual. The task attracted 163 participants. We received 70 submissions in total (across all tasks) from 51 different teams, and 38 system description papers. We report on the best-performing systems as well as the most common and the most effective approaches for the three different tracks. △ Less

Submitted 17 April, 2024; v1 submitted 27 March, 2024; originally announced March 2024.

Comments: SemEval 2024 Task Description Paper. arXiv admin note: text overlap with arXiv:2402.08638

DOSA: A Dataset of Social Artifacts from Different Indian Geographical Subcultures

Authors: Agrima Seth, Sanchit Ahuja, Kalika Bali, Sunayana Sitaram

Abstract: Generative models are increasingly being used in various applications, such as text generation, commonsense reasoning, and question-answering. To be effective globally, these models must be aware of and account for local socio-cultural contexts, making it necessary to have benchmarks to evaluate the models for their cultural familiarity. Since the training data for LLMs is web-based and the Web is… ▽ More Generative models are increasingly being used in various applications, such as text generation, commonsense reasoning, and question-answering. To be effective globally, these models must be aware of and account for local socio-cultural contexts, making it necessary to have benchmarks to evaluate the models for their cultural familiarity. Since the training data for LLMs is web-based and the Web is limited in its representation of information, it does not capture knowledge present within communities that are not on the Web. Thus, these models exacerbate the inequities, semantic misalignment, and stereotypes from the Web. There has been a growing call for community-centered participatory research methods in NLP. In this work, we respond to this call by using participatory research methods to introduce $\textit{DOSA}$, the first community-generated $\textbf{D}$ataset $\textbf{o}$f 615 $\textbf{S}$ocial $\textbf{A}$rtifacts, by engaging with 260 participants from 19 different Indian geographic subcultures. We use a gamified framework that relies on collective sensemaking to collect the names and descriptions of these artifacts such that the descriptions semantically align with the shared sensibilities of the individuals from those cultures. Next, we benchmark four popular LLMs and find that they show significant variation across regional sub-cultures in their ability to infer the artifacts. △ Less

Submitted 23 February, 2024; originally announced March 2024.

SemRel2024: A Collection of Semantic Textual Relatedness Datasets for 13 Languages

Authors: Nedjma Ousidhoum, Shamsuddeen Hassan Muhammad, Mohamed Abdalla, Idris Abdulmumin, Ibrahim Said Ahmad, Sanchit Ahuja, Alham Fikri Aji, Vladimir Araujo, Abinew Ali Ayele, Pavan Baswani, Meriem Beloucif, Chris Biemann, Sofia Bourhim, Christine De Kock, Genet Shanko Dekebo, Oumaima Hourrane, Gopichand Kanumolu, Lokesh Madasu, Samuel Rutunda, Manish Shrivastava, Thamar Solorio, Nirmal Surange, Hailegnaw Getaneh Tilaye, Krishnapriya Vishnubhotla, Genta Winata , et al. (2 additional authors not shown)

Abstract: Exploring and quantifying semantic relatedness is central to representing language and holds significant implications across various NLP tasks. While earlier NLP research primarily focused on semantic similarity, often within the English language context, we instead investigate the broader phenomenon of semantic relatedness. In this paper, we present \textit{SemRel}, a new semantic relatedness dat… ▽ More Exploring and quantifying semantic relatedness is central to representing language and holds significant implications across various NLP tasks. While earlier NLP research primarily focused on semantic similarity, often within the English language context, we instead investigate the broader phenomenon of semantic relatedness. In this paper, we present \textit{SemRel}, a new semantic relatedness dataset collection annotated by native speakers across 13 languages: \textit{Afrikaans, Algerian Arabic, Amharic, English, Hausa, Hindi, Indonesian, Kinyarwanda, Marathi, Moroccan Arabic, Modern Standard Arabic, Spanish,} and \textit{Telugu}. These languages originate from five distinct language families and are predominantly spoken in Africa and Asia -- regions characterised by a relatively limited availability of NLP resources. Each instance in the SemRel datasets is a sentence pair associated with a score that represents the degree of semantic textual relatedness between the two sentences. The scores are obtained using a comparative annotation framework. We describe the data collection and annotation processes, challenges when building the datasets, baseline experiments, and their impact and utility in NLP. △ Less

Submitted 31 May, 2024; v1 submitted 13 February, 2024; originally announced February 2024.

Comments: Accepted to the Findings of ACL 2024

Why Doesn't Microsoft Let Me Sleep? How Automaticity of Windows Updates Impacts User Autonomy

Authors: Sanju Ahuja, Ridhi Jain, Jyoti Kumar

Abstract: 'Automating the user away' has been designated as a dark pattern in literature for performing tasks without user consent or confirmation. However, limited studies have been reported on how users experience the sense of autonomy when digital systems fully or partially bypass consent. More research is required to understand what makes automaticity a threat to autonomy. To address this gap, a qualita… ▽ More 'Automating the user away' has been designated as a dark pattern in literature for performing tasks without user consent or confirmation. However, limited studies have been reported on how users experience the sense of autonomy when digital systems fully or partially bypass consent. More research is required to understand what makes automaticity a threat to autonomy. To address this gap, a qualitative interview study with 10 users was conducted to investigate the user experience of Microsoft Windows updates. It was found that ten design features of Windows updates impact the autonomy experience. For each design feature, the contextual factors which influence its impact on autonomy were also noted. The findings of this paper can help designers understand the ethical concerns posed by automaticity in design and identify measures to mitigate these concerns. △ Less

Submitted 12 January, 2024; originally announced January 2024.

Comments: 6 pages, 2 figures

MEGAVERSE: Benchmarking Large Language Models Across Languages, Modalities, Models and Tasks

Authors: Sanchit Ahuja, Divyanshu Aggarwal, Varun Gumma, Ishaan Watts, Ashutosh Sathe, Millicent Ochieng, Rishav Hada, Prachi Jain, Maxamed Axmed, Kalika Bali, Sunayana Sitaram

Abstract: There has been a surge in LLM evaluation research to understand LLM capabilities and limitations. However, much of this research has been confined to English, leaving LLM building and evaluation for non-English languages relatively unexplored. Several new LLMs have been introduced recently, necessitating their evaluation on non-English languages. This study aims to perform a thorough evaluation of… ▽ More There has been a surge in LLM evaluation research to understand LLM capabilities and limitations. However, much of this research has been confined to English, leaving LLM building and evaluation for non-English languages relatively unexplored. Several new LLMs have been introduced recently, necessitating their evaluation on non-English languages. This study aims to perform a thorough evaluation of the non-English capabilities of SoTA LLMs (GPT-3.5-Turbo, GPT-4, PaLM2, Gemini-Pro, Mistral, Llama2, and Gemma) by comparing them on the same set of multilingual datasets. Our benchmark comprises 22 datasets covering 83 languages, including low-resource African languages. We also include two multimodal datasets in the benchmark and compare the performance of LLaVA models, GPT-4-Vision and Gemini-Pro-Vision. Our experiments show that larger models such as GPT-4, Gemini-Pro and PaLM2 outperform smaller models on various tasks, notably on low-resource languages, with GPT-4 outperforming PaLM2 and Gemini-Pro on more datasets. We also perform a study on data contamination and find that several models are likely to be contaminated with multilingual evaluation benchmarks, necessitating approaches to detect and handle contamination while assessing the multilingual performance of LLMs. △ Less

Submitted 2 April, 2024; v1 submitted 13 November, 2023; originally announced November 2023.

Comments: 40 pages, 35 figures and 34 tables

Scalable and Safe Remediation of Defective Actions in Self-Learning Conversational Systems

Authors: Sarthak Ahuja, Mohammad Kachuee, Fateme Sheikholeslami, Weiqing Liu, Jaeyoung Do

Abstract: Off-Policy reinforcement learning has been a driving force for the state-of-the-art conversational AIs leading to more natural humanagent interactions and improving the user satisfaction for goal-oriented agents. However, in large-scale commercial settings, it is often challenging to balance between policy improvements and experience continuity on the broad spectrum of applications handled by such… ▽ More Off-Policy reinforcement learning has been a driving force for the state-of-the-art conversational AIs leading to more natural humanagent interactions and improving the user satisfaction for goal-oriented agents. However, in large-scale commercial settings, it is often challenging to balance between policy improvements and experience continuity on the broad spectrum of applications handled by such system. In the literature, off-policy evaluation and guard-railing on aggregate statistics has been commonly used to address this problem. In this paper, we propose a method for curating and leveraging high-precision samples sourced from historical regression incident reports to validate, safe-guard, and improve policies prior to the online deployment. We conducted extensive experiments using data from a real-world conversational system and actual regression incidents. The proposed method is currently deployed in our production system to protect customers against broken experiences and enable long-term policy improvements. △ Less

Submitted 17 May, 2023; originally announced May 2023.

Comments: Accepted at ACL 2023 Industry Track

Leveraging Large Language Models in Conversational Recommender Systems

Authors: Luke Friedman, Sameer Ahuja, David Allen, Zhenning Tan, Hakim Sidahmed, Changbo Long, Jun Xie, Gabriel Schubiner, Ajay Patel, Harsh Lara, Brian Chu, Zexi Chen, Manoj Tiwari

Abstract: A Conversational Recommender System (CRS) offers increased transparency and control to users by enabling them to engage with the system through a real-time multi-turn dialogue. Recently, Large Language Models (LLMs) have exhibited an unprecedented ability to converse naturally and incorporate world knowledge and common-sense reasoning into language understanding, unlocking the potential of this pa… ▽ More A Conversational Recommender System (CRS) offers increased transparency and control to users by enabling them to engage with the system through a real-time multi-turn dialogue. Recently, Large Language Models (LLMs) have exhibited an unprecedented ability to converse naturally and incorporate world knowledge and common-sense reasoning into language understanding, unlocking the potential of this paradigm. However, effectively leveraging LLMs within a CRS introduces new technical challenges, including properly understanding and controlling a complex conversation and retrieving from external sources of information. These issues are exacerbated by a large, evolving item corpus and a lack of conversational data for training. In this paper, we provide a roadmap for building an end-to-end large-scale CRS using LLMs. In particular, we propose new implementations for user preference understanding, flexible dialogue management and explainable recommendations as part of an integrated architecture powered by LLMs. For improved personalization, we describe how an LLM can consume interpretable natural language user profiles and use them to modulate session-level context. To overcome conversational data limitations in the absence of an existing production CRS, we propose techniques for building a controllable LLM-based user simulator to generate synthetic conversations. As a proof of concept we introduce RecLLM, a large-scale CRS for YouTube videos built on LaMDA, and demonstrate its fluency and diverse functionality through some illustrative example conversations. △ Less

Submitted 16 May, 2023; v1 submitted 13 May, 2023; originally announced May 2023.

Scalable and Robust Self-Learning for Skill Routing in Large-Scale Conversational AI Systems

Authors: Mohammad Kachuee, Jinseok Nam, Sarthak Ahuja, Jin-Myung Won, Sungjin Lee

Abstract: Skill routing is an important component in large-scale conversational systems. In contrast to traditional rule-based skill routing, state-of-the-art systems use a model-based approach to enable natural conversations. To provide supervision signal required to train such models, ideas such as human annotation, replication of a rule-based system, relabeling based on user paraphrases, and bandit-based… ▽ More Skill routing is an important component in large-scale conversational systems. In contrast to traditional rule-based skill routing, state-of-the-art systems use a model-based approach to enable natural conversations. To provide supervision signal required to train such models, ideas such as human annotation, replication of a rule-based system, relabeling based on user paraphrases, and bandit-based learning were suggested. However, these approaches: (a) do not scale in terms of the number of skills and skill on-boarding, (b) require a very costly expert annotation/rule-design, (c) introduce risks in the user experience with each model update. In this paper, we present a scalable self-learning approach to explore routing alternatives without causing abrupt policy changes that break the user experience, learn from the user interaction, and incrementally improve the routing via frequent model refreshes. To enable such robust frequent model updates, we suggest a simple and effective approach that ensures controlled policy updates for individual domains, followed by an off-policy evaluation for making deployment decisions without any need for lengthy A/B experimentation. We conduct various offline and online A/B experiments on a commercial large-scale conversational system to demonstrate the effectiveness of the proposed method in real-world production settings. △ Less

Submitted 14 April, 2022; originally announced April 2022.

Comments: NAACL 2022

Parametric Variational Linear Units (PVLUs) in Deep Convolutional Networks

Authors: Aarush Gupta, Shikhar Ahuja

Abstract: The Rectified Linear Unit is currently a state-of-the-art activation function in deep convolutional neural networks. To combat ReLU's dying neuron problem, we propose the Parametric Variational Linear Unit (PVLU), which adds a sinusoidal function with trainable coefficients to ReLU. Along with introducing nonlinearity and non-zero gradients across the entire real domain, PVLU acts as a mechanism o… ▽ More The Rectified Linear Unit is currently a state-of-the-art activation function in deep convolutional neural networks. To combat ReLU's dying neuron problem, we propose the Parametric Variational Linear Unit (PVLU), which adds a sinusoidal function with trainable coefficients to ReLU. Along with introducing nonlinearity and non-zero gradients across the entire real domain, PVLU acts as a mechanism of fine-tuning when implemented in the context of transfer learning. On a simple, non-transfer sequential CNN, PVLU substitution allowed for relative error decreases of 16.3% and 11.3% (without and with data augmentation) on CIFAR-100. PVLU is also tested on transfer learning models. The VGG-16 and VGG-19 models experience relative error reductions of 9.5% and 10.7% on CIFAR-10, respectively, after the substitution of ReLU with PVLU. When training on Gaussian-filtered CIFAR-10 images, similar improvements are noted for the VGG models. Most notably, fine-tuning using PVLU allows for relative error reductions up to and exceeding 10% for near state-of-the-art residual neural network architectures on the CIFAR datasets. △ Less

Submitted 16 December, 2021; v1 submitted 23 October, 2021; originally announced October 2021.

Comments: Both authors contributed equally to this research

Cogniculture: Towards a Better Human-Machine Co-evolution

Authors: Rakesh R Pimplikar, Kushal Mukherjee, Gyana Parija, Harit Vishwakarma, Ramasuri Narayanam, Sarthak Ahuja, Rohith D Vallam, Ritwik Chaudhuri, Joydeep Mondal

Abstract: Research in Artificial Intelligence is breaking technology barriers every day. New algorithms and high performance computing are making things possible which we could only have imagined earlier. Though the enhancements in AI are making life easier for human beings day by day, there is constant fear that AI based systems will pose a threat to humanity. People in AI community have diverse set of opi… ▽ More Research in Artificial Intelligence is breaking technology barriers every day. New algorithms and high performance computing are making things possible which we could only have imagined earlier. Though the enhancements in AI are making life easier for human beings day by day, there is constant fear that AI based systems will pose a threat to humanity. People in AI community have diverse set of opinions regarding the pros and cons of AI mimicking human behavior. Instead of worrying about AI advancements, we propose a novel idea of cognitive agents, including both human and machines, living together in a complex adaptive ecosystem, collaborating on human computation for producing essential social goods while promoting sustenance, survival and evolution of the agents' life cycle. We highlight several research challenges and technology barriers in achieving this goal. We propose a governance mechanism around this ecosystem to ensure ethical behaviors of all cognitive agents. Along with a novel set of use-cases of Cogniculture, we discuss the road map ahead for this journey. △ Less

Submitted 11 December, 2017; originally announced December 2017.

3D Scan Registration using Curvelet Features in Planetary Environments

Authors: Siddhant Ahuja, Peter Iles, Steven L. Waslander

Abstract: Topographic mapping in planetary environments relies on accurate 3D scan registration methods. However, most global registration algorithms relying on features such as FPFH and Harris-3D show poor alignment accuracy in these settings due to the poor structure of the Mars-like terrain and variable resolution, occluded, sparse range data that is hard to register without some a-priori knowledge of th… ▽ More Topographic mapping in planetary environments relies on accurate 3D scan registration methods. However, most global registration algorithms relying on features such as FPFH and Harris-3D show poor alignment accuracy in these settings due to the poor structure of the Mars-like terrain and variable resolution, occluded, sparse range data that is hard to register without some a-priori knowledge of the environment. In this paper, we propose an alternative approach to 3D scan registration using the curvelet transform that performs multi-resolution geometric analysis to obtain a set of coefficients indexed by scale (coarsest to finest), angle and spatial position. Features are detected in the curvelet domain to take advantage of the directional selectivity of the transform. A descriptor is computed for each feature by calculating the 3D spatial histogram of the image gradients, and nearest neighbor based matching is used to calculate the feature correspondences. Correspondence rejection using Random Sample Consensus identifies inliers, and a locally optimal Singular Value Decomposition-based estimation of the rigid-body transformation aligns the laser scans given the re-projected correspondences in the metric space. Experimental results on a publicly available data-set of planetary analogue indoor facility, as well as simulated and real-world scans from Neptec Design Group's IVIGMS 3D laser rangefinder at the outdoor CSA Mars yard demonstrates improved performance over existing methods in the challenging sparse Mars-like terrain. △ Less

Submitted 23 September, 2015; originally announced September 2015.

Comments: 27 pages in Journal of Field Robotics, 2015

Information Retrieval in Intelligent Systems: Current Scenario & Issues

Authors: Sudhir Ahuja, Mr. Rinkaj Goyal

Abstract: Web space is the huge repository of data. Everyday lots of new information get added to this web space. The more the information, more is demand for tools to access that information. Answering users' queries about the online information intelligently is one of the great challenges in information retrieval in intelligent systems. In this paper, we will start with the brief introduction on informati… ▽ More Web space is the huge repository of data. Everyday lots of new information get added to this web space. The more the information, more is demand for tools to access that information. Answering users' queries about the online information intelligently is one of the great challenges in information retrieval in intelligent systems. In this paper, we will start with the brief introduction on information retrieval and intelligent systems and explain how swoogle, the semantic search engine, uses its algorithms and techniques to search for the desired contents in the web. We then continue with the clustering technique that is used to group the similar things together and discuss the machine learning technique called Self-organizing maps [6] or SOM, which is a data visualization technique that reduces the dimensions of data through the use of self-organizing neural networks. We then discuss how SOM is used to visualize the contents of the data, by following some lines of algorithm, in the form of maps. So, we could say that websites or machines can be used to retrieve the information that what exactly users want from them. △ Less

Submitted 16 June, 2012; originally announced June 2012.

Bio-Authentication based Secure Transmission System using Steganography

Authors: Najme Zehra, Mansi Sharma, Somya Ahuja, Shubha Bansal

Abstract: Biometrics deals with identity verification of an individual by using certain physiological or behavioral features associated with a person. Biometric identification systems using fingerprints patterns are called AFIS (Automatic Fingerprint Identification System). In this paper a composite method for Fingerprint recognition is considered using a combination of Fast Fourier Transform (FFT) and Sobe… ▽ More Biometrics deals with identity verification of an individual by using certain physiological or behavioral features associated with a person. Biometric identification systems using fingerprints patterns are called AFIS (Automatic Fingerprint Identification System). In this paper a composite method for Fingerprint recognition is considered using a combination of Fast Fourier Transform (FFT) and Sobel Filters for improvement of a poor quality fingerprint image. Steganography hides messages inside other messages in such a way that an "adversary" would not even know a secret message were present. The objective of our paper is to make a bio-secure system. In this paper bio-authentication has been implemented in terms of finger print recognition and the second part of the paper is an interactive steganographic system hides the user's data by two options- creating a songs list or hiding the data in an image. △ Less

Submitted 24 May, 2010; originally announced May 2010.

Comments: IEEE Publication format, International Journal of Computer Science and Information Security, IJCSIS, Vol. 8 No. 1, April 2010, USA. ISSN 1947 5500, http://sites.google.com/site/ijcsis/