English
Related papers

Related papers: Emergent Hierarchical Structure in Large Language …

200 papers

Autoregressive language models achieve remarkable performance, yet a unified theory explaining their internal mechanisms, how training shapes representations, and why these representations support complex behavior remains incomplete. We…

Machine Learning · Computer Science 2026-05-14 Yifan Zhang

Recent research has adopted a new experimental field centered around the concept of text perturbations which has revealed that shuffled word order has little to no impact on the downstream performance of Transformer-based language models…

Computation and Language · Computer Science 2023-10-04 Ekaterina Taktasheva , Vladislav Mikhailov , Ekaterina Artemova

Language models based on the Transformer architecture achieve excellent results in many language-related tasks, such as text classification or sentiment analysis. However, despite the architecture of these models being well-defined, little…

Computation and Language · Computer Science 2025-04-14 Miguel López-Otal , Jorge Gracia , Jordi Bernad , Carlos Bobed , Lucía Pitarch-Ballesteros , Emma Anglés-Herrero

Large Language Models (LLMs) have an unrivaled and invaluable ability to "align" their output to a diverse range of human preferences, by mirroring them in the text they generate. The internal characteristics of such models, however, remain…

Computation and Language · Computer Science 2024-07-08 Brenden Smith , Dallin Baker , Clayton Chase , Myles Barney , Kaden Parker , Makenna Allred , Peter Hu , Alex Evans , Nancy Fulda

Multilingual large language models (LLMs) have minimized the fluency gap between languages. This advancement, however, exposes models to the risk of biased behavior, as knowledge and norms may propagate across languages. In this work, we…

Computation and Language · Computer Science 2026-04-22 Guy Mor-Lan , Omer Goldman , Matan Eyal , Adi Mayrav Gilady , Sivan Eiger , Idan Szpektor , Avinatan Hassidim , Yossi Matias , Reut Tsarfaty

Bytes form the basis of the digital world and thus are a promising building block for multimodal foundation models. Recently, Byte Language Models (BLMs) have emerged to overcome tokenization, yet the excessive length of bytestreams…

Computation and Language · Computer Science 2025-02-21 Eric Egli , Matteo Manica , Jannis Born

It has been found that Transformer-based language models have the ability to perform basic quantitative reasoning. In this paper, we propose a method for studying how these models internally represent numerical data, and use our proposal to…

Computation and Language · Computer Science 2024-04-26 Ulme Wennberg , Gustav Eje Henter

Large language models (LLMs) achieve impressive results in terms of fluency in text generation, yet the nature of their linguistic knowledge - in particular the human-likeness of their internal lexicon - remains uncertain. This study…

Computation and Language · Computer Science 2026-03-20 Maria Andueza Rodriguez , Marie Candito , Richard Huyghe

Understanding how Large Language Models (LLMs) perform logical reasoning internally remains a fundamental challenge. While prior mechanistic studies focus on identifying taskspecific circuits, they leave open the question of what…

Artificial Intelligence · Computer Science 2026-01-09 Danchun Chen , Qiyao Yan , Liangming Pan

Self-evolving large language model (LLM) agents continually improve by accumulating and reusing past experience, yet it remains unclear whether they faithfully rely on that experience to guide their behavior. We present the first systematic…

Computation and Language · Computer Science 2026-02-10 Weixiang Zhao , Yingshuo Wang , Yichen Zhang , Yang Deng , Yanyan Zhao , Wanxiang Che , Bing Qin , Ting Liu

Large language models (LLMs) show remarkable capabilities across a variety of tasks. Despite the models only seeing text in training, several recent studies suggest that LLM representations implicitly capture aspects of the underlying…

Computation and Language · Computer Science 2024-04-16 Yutaro Yamada , Yihan Bao , Andrew K. Lampinen , Jungo Kasai , Ilker Yildirim

Low-resource languages (LRLs) face significant challenges in natural language processing (NLP) due to limited data. While current state-of-the-art large language models (LLMs) still struggle with LRLs, smaller multilingual models (mLMs)…

Computation and Language · Computer Science 2025-02-17 Daniil Gurgurov , Ivan Vykopal , Josef van Genabith , Simon Ostermann

Large language models (LLMs) perform well on multi-hop reasoning, yet how they internally compose multiple facts remains unclear. Recent work proposes \emph{hop-aligned circuit hypothesis}, suggesting that bridge entities are computed…

Computation and Language · Computer Science 2026-01-08 Xukai Liu , Ye Liu , Jipeng Zhang , Yanghai Zhang , Kai Zhang , Qi Liu

Large Language Models (LLMs) increasingly serve as autonomous reasoning agents in decision support, scientific problem-solving, and multi-agent coordination systems. However, deploying LLM agents in consequential applications requires…

Artificial Intelligence · Computer Science 2026-03-17 I. de Zarzà , J. de Curtò , Jordi Cabot , Pietro Manzoni , Carlos T. Calafate

Multiscale feature hierarchies have been witnessed the success in the computer vision area. This further motivates researchers to design multiscale Transformer for natural language processing, mostly based on the self-attention mechanism.…

Computation and Language · Computer Science 2022-06-22 Bei Li , Tong Zheng , Yi Jing , Chengbo Jiao , Tong Xiao , Jingbo Zhu

Large language models based on transformers have achieved great empirical successes. However, as they are deployed more widely, there is a growing need to better understand their internal mechanisms in order to make them more reliable.…

Machine Learning · Statistics 2023-11-08 Alberto Bietti , Vivien Cabannes , Diane Bouchacourt , Herve Jegou , Leon Bottou

We study the fractal structure of language, aiming to provide a precise formalism for quantifying properties that may have been previously suspected but not formally shown. We establish that language is: (1) self-similar, exhibiting…

Computation and Language · Computer Science 2024-05-24 Ibrahim Alabdulmohsin , Vinh Q. Tran , Mostafa Dehghani

We present Multi-Scale Manifold Alignment(MSMA), an information-geometric framework that decomposes LLM representations into local, intermediate, and global manifolds and learns cross-scale mappings that preserve geometry and information.…

Computation and Language · Computer Science 2025-10-14 Yukun Zhang , Qi Dong

Existing interpretability methods for Large Language Models (LLMs) predominantly capture linear directions or isolated features. This overlooks the high-dimensional, relational, and nonlinear geometry of model representations. We apply…

Machine Learning · Computer Science 2026-04-27 Aideen Fay , Inés García-Redondo , Qiquan Wang , Haim Dubossarsky , Anthea Monod

Large language models (LLMs) achieve remarkable fluency across linguistic and reasoning tasks but remain systematically prone to hallucination. Prevailing accounts attribute hallucinations to data gaps, limited context, or optimization…

Computers and Society · Computer Science 2025-09-23 Richard Ackermann , Simeon Emanuilov