English
Related papers

Related papers: Not All Language Model Features Are One-Dimensiona…

200 papers

Molecular dynamics (MD) is a powerful approach for modelling molecular systems, but it remains computationally intensive on spatial and time scales of many macromolecular systems of biological interest. To explore the opportunities offered…

Biomolecules · Quantitative Biology 2025-08-07 Mhd Hussein Murtada , Z. Faidon Brotzakis , Michele Vendruscolo

Large language models (LLMs) were invented for natural language tasks such as translation, but they have proved that they can perform highly complex functions across domains. Additionally, they have been thought to develop new skills…

Computation and Language · Computer Science 2026-05-12 Jung H. Lee , Sujith Vijayan

Large Language Models (LLMs) achieve strong linguistic performance, yet their internal mechanisms for producing these predictions remain unclear. We investigate the hypothesis that LLMs encode representations of linguistic constraint…

Computation and Language · Computer Science 2026-05-15 Hardy , Sebastian Padó

Powerful sentence encoders trained for multiple languages are on the rise. These systems are capable of embedding a wide range of linguistic properties into vector representations. While explicit probing tasks can be used to verify the…

Computation and Language · Computer Science 2021-09-22 Maarten De Raedt , Fréderic Godin , Pieter Buteneers , Chris Develder , Thomas Demeester

Large language models exhibit strong multilingual capabilities despite limited exposure to non-English data. Prior studies show that English-centric large language models map multilingual content into English-aligned representations at…

Computation and Language · Computer Science 2026-01-30 Chengzhi Zhong , Fei Cheng , Qianying Liu , Yugo Murawaki , Chenhui Chu , Sadao Kurohashi

We demonstrate that sparse autoencoders can extract interpretable features from Claude 3 Sonnet, a production-scale language model, addressing the open question of whether dictionary learning methods scale beyond small transformers. We…

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

There is a large ongoing scientific effort in mechanistic interpretability to map embeddings and internal representations of AI systems into human-understandable concepts. A key element of this effort is the linear representation…

Machine Learning · Computer Science 2025-05-27 Alexander Modell , Patrick Rubin-Delanchy , Nick Whiteley

Distributed representations of words have been shown to capture lexical semantics, as demonstrated by their effectiveness in word similarity and analogical relation tasks. But, these tasks only evaluate lexical semantics indirectly. In this…

Computation and Language · Computer Science 2016-12-02 Thanapon Noraset , Chen Liang , Larry Birnbaum , Doug Downey

Multiword expressions, characterised by non-compositional meanings and syntactic irregularities, are an example of nuanced language. These expressions can be used literally or idiomatically, leading to significant changes in meaning. While…

Computation and Language · Computer Science 2025-04-30 Frances Laureano De Leon , Harish Tayyar Madabushi , Mark G. Lee

Large Language Models (LLMs) have demonstrated unprecedented capabilities across various natural language processing tasks. Their ability to process and generate viable text and code has made them ubiquitous in many fields, while their…

Machine Learning · Computer Science 2025-05-13 Stef De Sabbata , Stefano Mizzaro , Kevin Roitero

Recent advances in Large Language Models (LLMs) have opened new perspectives for automation in optimization. While several studies have explored how LLMs can generate or solve optimization models, far less is understood about what these…

Artificial Intelligence · Computer Science 2025-12-16 Francesca Da Ros , Luca Di Gaspero , Kevin Roitero

Automated interpretability pipelines generate natural language descriptions for the concepts represented by features in large language models (LLMs), such as plants or the first word in a sentence. These descriptions are derived using…

Computation and Language · Computer Science 2025-05-30 Yoav Gur-Arieh , Roy Mayan , Chen Agassy , Atticus Geiger , Mor Geva

The importance of explainability in machine learning continues to grow, as both neural-network architectures and the data they model become increasingly complex. Unique challenges arise when a model's input features become high dimensional:…

Machine Learning · Computer Science 2021-12-21 Damien de Mijolla , Christopher Frye , Markus Kunesch , John Mansir , Ilya Feige

In recent years several novel models were developed to process natural language, development of accurate language translation systems have helped us overcome geographical barriers and communicate ideas effectively. These models are…

Computation and Language · Computer Science 2019-02-19 Sangarshanan Veeraraghavan

Spatial consistency is a fundamental property of the visual world and a key requirement for models that aim to understand physical reality. Despite recent advances, multimodal large language models (MLLMs) often struggle to reason about 3D…

Computer Vision and Pattern Recognition · Computer Science 2026-04-06 Om Khangaonkar , Hadi J. Rad , Hamed Pirsiavash

Language exhibits a fractal structure in its information-theoretic complexity (i.e. bits per token), with self-similarity across scales and long-range dependence (LRD). In this work, we investigate whether large language models (LLMs) can…

Computation and Language · Computer Science 2025-05-27 Ibrahim Alabdulmohsin , Andreas Steiner

Through extensive experience developing and explaining machine learning (ML) applications for real-world domains, we have learned that ML models are only as interpretable as their features. Even simple, highly interpretable model types such…

Machine Learning · Computer Science 2022-02-25 Alexandra Zytek , Ignacio Arnaldo , Dongyu Liu , Laure Berti-Equille , Kalyan Veeramachaneni

High-dimensional representations for words, text, images, knowledge graphs and other structured data are commonly used in different paradigms of machine learning and data mining. These representations have different degrees of…

Computation and Language · Computer Science 2020-11-26 Sunipa Dev

Large language models (LLMs) work by manipulating the geometry of input embedding vectors over multiple layers. Here, we ask: how are the input vocabulary representations of language models structured, and how and when does this structure…

Computation and Language · Computer Science 2025-10-10 Isabel Papadimitriou , Jacob Prince