Skip to main content
arXiv is now an independent nonprofit! Learn more

Showing 1–11 of 11 results for author: Urrutia, F

Searching in archive cs. Search in all archives.
.
  1. arXiv:2607.22361  [pdf, ps, other

    cs.LG cs.AI

    Indexing: the Beginning and the End

    Authors: Alexander Kozachinskiy, Vicente Opazo, Felipe Urrutia

    Abstract: We study information bottlenecks in modern deep-learning architectures -- RNNs, softmax transformers, linear-attention transformers and state-space models -- through the lens of the indexing primitive. In this primitive, the input consists of $n$ bits and one integer $i$ from $1$ to $n$ called the index, and the output equals the value of the $i$-th bit. We introduce causal complexity for masked… ▽ More

    Submitted 24 July, 2026; originally announced July 2026.

  2. arXiv:2605.31558  [pdf, ps, other

    cs.LG cs.AI

    Positional versus Symbolic Attention Heads: Learning Dynamics, RoPE Geometry, and Length Generalization

    Authors: Felipe Urrutia, Juan José Alegría, Cinthia Sanchez Macias, Jorge Salas, Cristian B. Calderon, Cristobal Rojas

    Abstract: Transformer-based language models are widespread in today's society. As such, understanding the mechanisms by which they solve structured tasks and predicting how they may behave in novel scenarios is of great importance for safe deployment. We study the learning dynamics of attention heads in a controlled setting by training a decoder-only Transformer (GPT-J) on two structurally equivalent multi-… ▽ More

    Submitted 29 May, 2026; originally announced May 2026.

  3. arXiv:2511.11579  [pdf, ps, other

    cs.LG cs.AI cs.CL

    Decoupling Positional and Symbolic Attention Behavior in Transformers

    Authors: Felipe Urrutia, Jorge Salas, Alexander Kozachinskiy, Cristian Buc Calderon, Hector Pasten, Cristobal Rojas

    Abstract: An important aspect subtending language understanding and production is the ability to independently encode positional and symbolic information of the words within a sentence. In Transformers, positional information is typically encoded using Positional Encodings (PEs). One such popular PE, namely Rotary PE (RoPE), has been widely used due to its empirical success. Recently, it has been argued tha… ▽ More

    Submitted 2 October, 2025; originally announced November 2025.

    Comments: 32 pages, 12 figures, repository available

    MSC Class: 03D78 ACM Class: I.2.0; F.1.0

  4. arXiv:2505.10606  [pdf, ps, other

    cs.LG cs.AI

    Continuity and Isolation Lead to Doubts or Dilemmas in Large Language Models

    Authors: Hector Pasten, Felipe Urrutia, Hector Jimenez, Cristian B. Calderon, Cristóbal Rojas, Alexander Kozachinskiy

    Abstract: Understanding how Transformers work and how they process information is key to the theoretical and empirical advancement of these machines. In this work, we demonstrate the existence of two phenomena in Transformers, namely isolation and continuity. Both of these phenomena hinder Transformers to learn even simple pattern sequences. Isolation expresses that any learnable sequence must be isolated f… ▽ More

    Submitted 15 May, 2025; originally announced May 2025.

  5. arXiv:2501.19215  [pdf, ps, other

    cs.LG cs.AI

    Strassen Attention, Split VC Dimension and Compositionality in Transformers

    Authors: Alexander Kozachinskiy, Felipe Urrutia, Hector Jimenez, Tomasz Steifer, Germán Pizarro, Matías Fuentes, Francisco Meza, Cristian B. Calderon, Cristóbal Rojas

    Abstract: We propose the first method to show theoretical limitations for one-layer softmax transformers with arbitrarily many precision bits (even infinite). We establish those limitations for three tasks that require advanced reasoning. The first task, Match 3 (Sanford et al., 2023), requires looking at all possible token triplets in an input sequence. The second and third tasks address compositionality-b… ▽ More

    Submitted 25 September, 2025; v1 submitted 31 January, 2025; originally announced January 2025.

    Comments: Accepted at NeurIPS 2025

  6. arXiv:2501.16247  [pdf, other

    cs.LG cs.CL

    Zero-Shot Decision Tree Construction via Large Language Models

    Authors: Lucas Carrasco, Felipe Urrutia, Andrés Abeliuk

    Abstract: This paper introduces a novel algorithm for constructing decision trees using large language models (LLMs) in a zero-shot manner based on Classification and Regression Trees (CART) principles. Traditional decision tree induction methods rely heavily on labeled data to recursively partition data using criteria such as information gain or the Gini index. In contrast, we propose a method that uses th… ▽ More

    Submitted 27 January, 2025; originally announced January 2025.

  7. Deep Natural Language Feature Learning for Interpretable Prediction

    Authors: Felipe Urrutia, Cristian Buc, Valentin Barriere

    Abstract: We propose a general method to break down a main complex task into a set of intermediary easier sub-tasks, which are formulated in natural language as binary questions related to the final target task. Our method allows for representing each example by a vector consisting of the answers to these questions. We call this representation Natural Language Learned Features (NLLF). NLLF is generated by a… ▽ More

    Submitted 9 November, 2023; originally announced November 2023.

  8. arXiv:2304.11257  [pdf

    cs.CL cs.AI cs.LG

    Who's the Best Detective? LLMs vs. MLs in Detecting Incoherent Fourth Grade Math Answers

    Authors: Felipe Urrutia, Roberto Araya

    Abstract: Written answers to open-ended questions can have a higher long-term effect on learning than multiple-choice questions. However, it is critical that teachers immediately review the answers, and ask to redo those that are incoherent. This can be a difficult task and can be time-consuming for teachers. A possible solution is to automate the detection of incoherent answers. One option is to automate t… ▽ More

    Submitted 21 April, 2023; originally announced April 2023.

  9. arXiv:1901.01178  [pdf, ps, other

    cs.CC

    A New Approach to Multi-Party Peer-to-Peer Communication Complexity

    Authors: Adi Rosén, Florent Urrutia

    Abstract: We introduce new models and new information theoretic measures for the study of communication complexity in the natural peer-to-peer, multi-party, number-in-hand setting. We prove a number of properties of our new models and measures, and then, in order to exemplify their effectiveness, we use them to prove two lower bounds. The more elaborate one is a tight lower bound of $Ω(kn)$ on the multi-par… ▽ More

    Submitted 30 September, 2020; v1 submitted 4 January, 2019; originally announced January 2019.

    Comments: ITCS 2019

  10. Improved Rectangular Matrix Multiplication using Powers of the Coppersmith-Winograd Tensor

    Authors: François Le Gall, Florent Urrutia

    Abstract: In the past few years, successive improvements of the asymptotic complexity of square matrix multiplication have been obtained by developing novel methods to analyze the powers of the Coppersmith-Winograd tensor, a basic construction introduced thirty years ago. In this paper we show how to generalize this approach to make progress on the complexity of rectangular matrix multiplication as well, by… ▽ More

    Submitted 6 November, 2017; v1 submitted 18 August, 2017; originally announced August 2017.

    Comments: 30 pages

    MSC Class: 68Q25 (Primary); 65F60 (Secondary) ACM Class: F.2.1

    Journal ref: Proceedings of the 29th ACM-SIAM Symposium on Discrete Algorithms (SODA 2018), pp. 1029-1046, 2018

  11. arXiv:1606.06872  [pdf, ps, other

    cs.CC cs.CR cs.IT

    Multi-Party Protocols, Information Complexity and Privacy

    Authors: Iordanis Kerenidis, Adi Rosén, Florent Urrutia

    Abstract: We introduce a new information theoretic measure that we call Public Information Complexity (PIC), as a tool for the study of multi-party computation protocols, and of quantities such as their communication complexity, or the amount of randomness they require in the context of information-theoretic private computations. We are able to use this measure directly in the natural asynchronous message-p… ▽ More

    Submitted 17 December, 2018; v1 submitted 22 June, 2016; originally announced June 2016.

    Comments: 32 pages ; MFCS2016 ; ACM Transactions on Computation Theory, to appear

    MSC Class: 94A05; 94A17 ACM Class: F.0; E.4