English
Related papers

Related papers: Categorical Perception in Large Language Model Hid…

200 papers

Learned Categorical Perception (CP) occurs when the members of different categories come to look more dissimilar (between-category separation) and/or members of the same category come to look more similar (within-category compression) after…

Neurons and Cognition · Quantitative Biology 2019-12-12 Fernanda Pérez-Gay , Tomy Sicotte , Christian Thériault , Stevan Harnad

Understanding the latent space geometry of large language models (LLMs) is key to interpreting their behavior and improving alignment. Yet it remains unclear to what extent LLMs linearly organize representations related to semantic…

Computation and Language · Computer Science 2026-01-22 Baturay Saglam , Paul Kassianik , Blaine Nelson , Sajana Weerawardhena , Yaron Singer , Amin Karbasi

Neural collapse ($\mathcal{NC}$) is a phenomenon observed in classification tasks where top-layer representations collapse into their class means, which become equinorm, equiangular and aligned with the classifiers. These behaviours --…

Machine Learning · Computer Science 2024-11-27 Robert Wu , Vardan Papyan

Continual Learning (CL) is essential for enabling self-evolving large language models (LLMs) to adapt and remain effective amid rapid knowledge growth. Yet, despite its importance, little attention has been given to establishing statistical…

Machine Learning · Computer Science 2025-10-29 Xiaofan Zhou , Lu Cheng

Large Language Models (LLMs) perform internal computations in continuous vector spaces yet produce discrete tokens -- a fundamental mismatch whose geometric consequences remain poorly understood. We develop a mathematical framework that…

Machine Learning · Computer Science 2026-03-25 Mohamed A. Mabrok

Predicting properties from coordinate-category data -- sets of vectors paired with categorical information -- is fundamental to computational science. In materials science, this challenge manifests as predicting properties like formation…

Materials Science · Physics 2025-07-10 Nawaf Alampara , Santiago Miret , Kevin Maik Jablonka

The geometric structure of latent representations in large language models (LLMs) is an active area of research, driven in part by its implications for model transparency and AI safety. Existing literature has focused mainly on general…

Machine Learning · Computer Science 2026-04-14 Benjamin J. Choi , Melanie Weber

Large language models (LLMs) exhibit remarkable flexibility: they can adapt to novel tasks from in-context examples without any parameter updates, a capability known as in-context learning (ICL). Prior work on synthetic tasks has shown that…

Computation and Language · Computer Science 2026-05-29 Hua-Dong Xiong , Li Ji-An , Robert C. Wilson , Kwonjoon Lee , Xue-Xin Wei

Humans are believed to perceive numbers on a logarithmic mental number line, where smaller values are represented with greater resolution than larger ones. This cognitive bias, supported by neuroscience and behavioral studies, suggests that…

Computation and Language · Computer Science 2025-02-25 H. V. AlquBoj , Hilal AlQuabeh , Velibor Bojkovic , Tatsuya Hiraoka , Ahmed Oumar El-Shangiti , Munachiso Nwadike , Kentaro Inui

Large language models (LLMs) have achieved remarkable progress in natural language generation, yet they continue to display puzzling behaviors -- such as repetition and incoherence -- even when exhibiting low perplexity. This highlights a…

Computation and Language · Computer Science 2025-10-27 Xin Du , Kumiko Tanaka-Ishii

Learning to categorize requires distinguishing category members from non-members by detecting the features that covary with membership. Whether this process can induce changes in perception is still a matter of debate. In prior studies, we…

Neurons and Cognition · Quantitative Biology 2025-08-18 F. Pérez-Gay , T. Sicotte , N. Goulet , X. Kang , S. Harnad

Why do language models from different architecture families respond so differently to the same perturbation? We argue that the answer is not scale, but \emph{how architecture shapes information compression}. Analyzing eight Transformer…

Computation and Language · Computer Science 2026-05-07 Yukin Zhang , Qi Dong , Kemu Xu

Large language models (LLMs) are becoming pervasive in everyday life, yet their propensity to reproduce biases inherited from training data remains a pressing concern. Prior investigations into bias in LLMs have focused on the association…

Computation and Language · Computer Science 2024-04-29 Messi H. J. Lee , Jacob M. Montgomery , Calvin K. Lai

Large language models (LLMs) encode vast amounts of world knowledge. However, since these models are trained on large swaths of internet data, they are at risk of inordinately capturing information about dominant groups. This imbalance can…

Computation and Language · Computer Science 2023-10-24 Pola Schwöbel , Jacek Golebiowski , Michele Donini , Cédric Archambeau , Danish Pruthi

While large language models (LLMs) are trained purely on textual data, prior work has shown that their internal representations can exhibit rich geometric structure in embedding space. Building on this line of work, we investigate whether…

Artificial Intelligence · Computer Science 2026-05-28 Simardeep Singh , Paras Chopra

Understanding how feature representations evolve across layers in large language models (LLMs) is key to improving their interpretability and robustness. While recent studies have identified critical layers linked to specific functions or…

Machine Learning · Computer Science 2025-06-06 Xuyuan Liu , Lei Hsiung , Yaoqing Yang , Yujun Yan

Conformal prediction (CP) is a powerful framework for quantifying uncertainty in machine learning models, offering reliable predictions with finite-sample coverage guarantees. When applied to classification, CP produces a prediction set of…

Machine Learning · Computer Science 2025-08-20 Floris den Hengst , Inès Blin , Majid Mohammadi , Syed Ihtesham Hussain Shah , Taraneh Younesian

Conformal prediction (CP) offers distribution-free uncertainty quantification for machine learning models, yet its interplay with fairness in downstream decision-making remains underexplored. Moving beyond CP as a standalone operation…

Machine Learning · Statistics 2026-02-20 Pengqi Liu , Zijun Yu , Mouloud Belbahri , Arthur Charpentier , Masoud Asgharian , Jesse C. Cresswell

A well-known perceptual consequence of categorization in humans and other animals, called categorical perception, is notably characterized by a within-category compression and a between-category separation: two items, close in input space,…

Machine Learning · Computer Science 2021-11-16 Laurent Bonnasse-Gahot , Jean-Pierre Nadal

Geometric analyses of large language model (LLM) representations reveal structured variation across depth but remain fundamentally correlational with respect to token prediction formation. Meanwhile, causal interventions expose…

Machine Learning · Computer Science 2026-05-27 Shahar Haim , Daniel C McNamee
‹ Prev 1 2 3 10 Next ›