-
NLP Datasets for Idiom and Figurative Language Tasks
Authors:
Blake Matheny,
Phuong Minh Nguyen,
Minh Le Nguyen,
Stephanie Reynolds
Abstract:
Idiomatic and figurative language form a large portion of colloquial speech and writing. With social media, this informal language has become more easily observable to people and trainers of large language models (LLMs) alike. While the advantage of large corpora seems like the solution to all machine learning and Natural Language Processing (NLP) problems, idioms and figurative language continue…
▽ More
Idiomatic and figurative language form a large portion of colloquial speech and writing. With social media, this informal language has become more easily observable to people and trainers of large language models (LLMs) alike. While the advantage of large corpora seems like the solution to all machine learning and Natural Language Processing (NLP) problems, idioms and figurative language continue to elude LLMs. Finetuning approaches are proving to be optimal, but better and larger datasets can help narrow this gap even further. The datasets presented in this paper provide one answer, while offering a diverse set of categories on which to build new models and develop new approaches. A selection of recent idiom and figurative language datasets were used to acquire a combined idiom list, which was used to retrieve context sequences from a large corpus. One large-scale dataset of potential idiomatic and figurative language expressions and two additional human-annotated datasets of definite idiomatic and figurative language expressions were created to evaluate the baseline ability of pre-trained language models in handling figurative meaning through idiom recognition (detection) tasks. The resulting datasets were post-processed for model agnostic training compatibility, utilized in training, and evaluated on slot labeling and sequence tagging.
△ Less
Submitted 2 December, 2025; v1 submitted 20 November, 2025;
originally announced November 2025.
-
Steps towards an Ecology for the Internet
Authors:
Anil Madhavapeddy,
Sam Reynolds,
Alec P. Christie,
David A. Coomes,
Michael W. Dales,
Patrick Ferris,
Ryan Gibb,
Hamed Haddadi,
Sadiq Jaffer,
Josh Millar,
Cyrus Omar,
William J. Sutherland,
Jon Crowcroft
Abstract:
The Internet has grown from a humble set of protocols for end-to-end connectivity into a critical global system with no builtin "immune system". In the next decade the Internet will likely grow to a trillion nodes and need protection from threats ranging from floods of fake generative data to AI-driven malware. Unfortunately, growing centralisation has lead to the breakdown of mutualism across the…
▽ More
The Internet has grown from a humble set of protocols for end-to-end connectivity into a critical global system with no builtin "immune system". In the next decade the Internet will likely grow to a trillion nodes and need protection from threats ranging from floods of fake generative data to AI-driven malware. Unfortunately, growing centralisation has lead to the breakdown of mutualism across the network, with surveillance capitalism now the dominant business model. We take lessons from from biological systems towards evolving a more resilient Internet that can integrate adaptation mechanisms into its fabric. We also contribute ideas for how the Internet might incorporate digital immune systems, including how software stacks might mutate to encourage more architectural diversity. We strongly advocate for the Internet to "re-decentralise" towards incentivising more mutualistic forms of communication.
△ Less
Submitted 6 June, 2025;
originally announced June 2025.
-
Breaking Distortion-free Watermarks in Large Language Models
Authors:
Shayleen Reynolds,
Hengzhi He,
Dung Daniel T. Ngo,
Saheed Obitayo,
Niccolò Dalmasso,
Guang Cheng,
Vamsi K. Potluru,
Manuela Veloso
Abstract:
In recent years, LLM watermarking has emerged as an attractive safeguard against AI-generated content, with promising applications in many real-world domains. However, there are growing concerns that the current LLM watermarking schemes are vulnerable to expert adversaries wishing to reverse-engineer the watermarking mechanisms. Prior work in breaking or stealing LLM watermarks mainly focuses on t…
▽ More
In recent years, LLM watermarking has emerged as an attractive safeguard against AI-generated content, with promising applications in many real-world domains. However, there are growing concerns that the current LLM watermarking schemes are vulnerable to expert adversaries wishing to reverse-engineer the watermarking mechanisms. Prior work in breaking or stealing LLM watermarks mainly focuses on the distribution-modifying algorithm of Kirchenbauer et al. (2023), which perturbs the logit vector before sampling. In this work, we focus on reverse-engineering the other prominent LLM watermarking scheme, distortion-free watermarking (Kuditipudi et al. 2024), which preserves the underlying token distribution by using a hidden watermarking key sequence. We demonstrate that, even under a more sophisticated watermarking scheme, it is possible to compromise the LLM and carry out a spoofing attack, i.e. generate a large number of (potentially harmful) texts that can be attributed to the original watermarked LLM. Specifically, we propose using adaptive prompting and a sorting-based algorithm to accurately recover the underlying secret key for watermarking the LLM. Our empirical findings on LLAMA-3.1-8B-Instruct, Mistral-7B-Instruct, Gemma-7b, and OPT-125M challenge the current theoretical claims on the robustness and usability of the distortion-free watermarking techniques.
△ Less
Submitted 12 June, 2025; v1 submitted 25 February, 2025;
originally announced February 2025.
-
AI in Investment Analysis: LLMs for Equity Stock Ratings
Authors:
Kassiani Papasotiriou,
Srijan Sood,
Shayleen Reynolds,
Tucker Balch
Abstract:
Investment Analysis is a cornerstone of the Financial Services industry. The rapid integration of advanced machine learning techniques, particularly Large Language Models (LLMs), offers opportunities to enhance the equity rating process. This paper explores the application of LLMs to generate multi-horizon stock ratings by ingesting diverse datasets. Traditional stock rating methods rely heavily o…
▽ More
Investment Analysis is a cornerstone of the Financial Services industry. The rapid integration of advanced machine learning techniques, particularly Large Language Models (LLMs), offers opportunities to enhance the equity rating process. This paper explores the application of LLMs to generate multi-horizon stock ratings by ingesting diverse datasets. Traditional stock rating methods rely heavily on the expertise of financial analysts, and face several challenges such as data overload, inconsistencies in filings, and delayed reactions to market events. Our study addresses these issues by leveraging LLMs to improve the accuracy and consistency of stock ratings. Additionally, we assess the efficacy of using different data modalities with LLMs for the financial domain.
We utilize varied datasets comprising fundamental financial, market, and news data from January 2022 to June 2024, along with GPT-4-32k (v0613) (with a training cutoff in Sep. 2021 to prevent information leakage). Our results show that our benchmark method outperforms traditional stock rating methods when assessed by forward returns, specially when incorporating financial fundamentals. While integrating news data improves short-term performance, substituting detailed news summaries with sentiment scores reduces token use without loss of performance. In many cases, omitting news data entirely enhances performance by reducing bias.
Our research shows that LLMs can be leveraged to effectively utilize large amounts of multimodal financial data, as showcased by their effectiveness at the stock rating prediction task. Our work provides a reproducible and efficient framework for generating accurate stock ratings, serving as a cost-effective alternative to traditional methods. Future work will extend to longer timeframes, incorporate diverse data, and utilize newer models for enhanced insights.
△ Less
Submitted 30 October, 2024;
originally announced November 2024.
-
FlowMind: Automatic Workflow Generation with LLMs
Authors:
Zhen Zeng,
William Watson,
Nicole Cho,
Saba Rahimi,
Shayleen Reynolds,
Tucker Balch,
Manuela Veloso
Abstract:
The rapidly evolving field of Robotic Process Automation (RPA) has made significant strides in automating repetitive processes, yet its effectiveness diminishes in scenarios requiring spontaneous or unpredictable tasks demanded by users. This paper introduces a novel approach, FlowMind, leveraging the capabilities of Large Language Models (LLMs) such as Generative Pretrained Transformer (GPT), to…
▽ More
The rapidly evolving field of Robotic Process Automation (RPA) has made significant strides in automating repetitive processes, yet its effectiveness diminishes in scenarios requiring spontaneous or unpredictable tasks demanded by users. This paper introduces a novel approach, FlowMind, leveraging the capabilities of Large Language Models (LLMs) such as Generative Pretrained Transformer (GPT), to address this limitation and create an automatic workflow generation system. In FlowMind, we propose a generic prompt recipe for a lecture that helps ground LLM reasoning with reliable Application Programming Interfaces (APIs). With this, FlowMind not only mitigates the common issue of hallucinations in LLMs, but also eliminates direct interaction between LLMs and proprietary data or code, thus ensuring the integrity and confidentiality of information - a cornerstone in financial services. FlowMind further simplifies user interaction by presenting high-level descriptions of auto-generated workflows, enabling users to inspect and provide feedback effectively. We also introduce NCEN-QA, a new dataset in finance for benchmarking question-answering tasks from N-CEN reports on funds. We used NCEN-QA to evaluate the performance of workflows generated by FlowMind against baseline and ablation variants of FlowMind. We demonstrate the success of FlowMind, the importance of each component in the proposed lecture recipe, and the effectiveness of user interaction and feedback in FlowMind.
△ Less
Submitted 16 March, 2024;
originally announced April 2024.
-
am-AMM: An Auction-Managed Automated Market Maker
Authors:
Austin Adams,
Ciamac C. Moallemi,
Sara Reynolds,
Dan Robinson
Abstract:
Automated market makers (AMMs) have emerged as the dominant market mechanism for trading on decentralized exchanges implemented on blockchains. This paper presents a single mechanism that targets two important unsolved problems for AMMs: reducing losses to informed orderflow, and maximizing revenue from uninformed orderflow. The ``auction-managed AMM'' works by running a censorship-resistant oncha…
▽ More
Automated market makers (AMMs) have emerged as the dominant market mechanism for trading on decentralized exchanges implemented on blockchains. This paper presents a single mechanism that targets two important unsolved problems for AMMs: reducing losses to informed orderflow, and maximizing revenue from uninformed orderflow. The ``auction-managed AMM'' works by running a censorship-resistant onchain auction for the right to temporarily act as ``pool manager'' for a constant-product AMM. The pool manager sets the swap fee rate on the pool, and also receives the accrued fees from swaps. The pool manager can exclusively capture some arbitrage by trading against the pool in response to small price movements, and also can set swap fees incorporating price sensitivity of retail orderflow and adapting to changing market conditions, with the benefits from both ultimately accruing to liquidity providers. Liquidity providers can enter and exit the pool freely in response to changing rent, though they must pay a small fee on withdrawal. We prove that under certain assumptions, this AMM should have higher liquidity in equilibrium than any standard, fixed-fee AMM.
△ Less
Submitted 12 February, 2025; v1 submitted 5 March, 2024;
originally announced March 2024.
-
Sexing Caucasian 2D footprints using convolutional neural networks
Authors:
Marcin Budka,
Matthew R. Bennet,
Sally Reynolds,
Shelby Barefoot,
Sarah Reel,
Selina Reidy,
Jeremy Walker
Abstract:
Footprints are left, or obtained, in a variety of scenarios from crime scenes to anthropological investigations. Determining the sex of a footprint can be useful in screening such impressions and attempts have been made to do so using single or multi landmark distances, shape analyses and via the density of friction ridges. Here we explore the relative importance of different components in sexing…
▽ More
Footprints are left, or obtained, in a variety of scenarios from crime scenes to anthropological investigations. Determining the sex of a footprint can be useful in screening such impressions and attempts have been made to do so using single or multi landmark distances, shape analyses and via the density of friction ridges. Here we explore the relative importance of different components in sexing two-dimensional foot impressions namely, size, shape and texture. We use a machine learning approach and compare this to more traditional methods of discrimination. Two datasets are used, a pilot data set collected from students at Bournemouth University (N=196) and a larger data set collected by podiatrists at Sheffield NHS Teaching Hospital (N=2677). Our convolutional neural network can sex a footprint with accuracy of around 90% on a test set of N=267 footprint images using all image components, which is better than an expert can achieve. However, the quality of the impressions impacts on this success rate, but the results are promising and in time it may be possible to create an automated screening algorithm in which practitioners of whatever sort (medical or forensic) can obtain a first order sexing of a two-dimensional footprint.
△ Less
Submitted 23 July, 2021;
originally announced August 2021.
-
A Visualization Interface to Improve the Transparency of Collected Personal Data on the Internet
Authors:
Marija Schufrin,
Steven Lamarr Reynolds,
Arjan Kuijper,
Jörn Kohlhammer
Abstract:
Online services are used for all kinds of activities, like news, entertainment, publishing content or connecting with others. But information technology enables new threats to privacy by means of global mass surveillance, vast databases and fast distribution networks. Current news are full of misuses and data leakages. In most cases, users are powerless in such situations and develop an attitude o…
▽ More
Online services are used for all kinds of activities, like news, entertainment, publishing content or connecting with others. But information technology enables new threats to privacy by means of global mass surveillance, vast databases and fast distribution networks. Current news are full of misuses and data leakages. In most cases, users are powerless in such situations and develop an attitude of neglect for their online behaviour. On the other hand, the GDPR (General Data Protection Regulation) gives users the right to request a copy of all their personal data stored by a particular service, but the received data is hard to understand or analyze by the common internet user. This paper presents TransparencyVis - a web-based interface to support the visual and interactive exploration of data exports from different online services. With this approach, we aim at increasing the awareness of personal data stored by such online services and the effects of online behaviour. This design study provides an online accessible prototype and a best practice to unify data exports from different sources.
△ Less
Submitted 8 September, 2022; v1 submitted 7 September, 2020;
originally announced September 2020.
-
Art Speaks Maths, Maths Speaks Art
Authors:
Ninetta Leone,
Simone Parisotto,
Kasia Targonska-Hadzibabic,
Spike Bucklow,
Alessandro Launaro,
Suzanne Reynolds,
Carola-Bibiane Schönlieb
Abstract:
Our interdisciplinary team Mathematics for Applications in Cultural Heritage (MACH) aims to use mathematical research for the benefit of the arts and humanities. Our ultimate goal is to create user-friendly software toolkits for artists, art conservators and archaeologists. In order for their underlying mathematical engines and functionality to be optimised for the needs of the end users, we pursu…
▽ More
Our interdisciplinary team Mathematics for Applications in Cultural Heritage (MACH) aims to use mathematical research for the benefit of the arts and humanities. Our ultimate goal is to create user-friendly software toolkits for artists, art conservators and archaeologists. In order for their underlying mathematical engines and functionality to be optimised for the needs of the end users, we pursue an iterative approach based on a continuous communication between the mathematicians and the cultural-heritage members of our team. Our paper illustrates how maths can speak art, but only if first art speaks maths.
△ Less
Submitted 17 July, 2020;
originally announced July 2020.