English
Related papers

Related papers: How Post-Training Reshapes LLMs: A Mechanistic Vie…

200 papers

Current techniques for post-training Large Language Models (LLMs) rely either on costly human supervision or on external verifiers to boost performance on tasks such as mathematical reasoning and code generation. However, as LLMs improve…

Computation and Language · Computer Science 2026-01-21 Mukesh Ghimire , Aosong Feng , Liwen You , Youzhi Luo , Fang Liu , Xuan Zhu

Language style is often used by writers to convey their intentions, identities, and mastery of language. In this paper, we show that current large language models struggle to capture some language styles without fine-tuning. To address this…

Computation and Language · Computer Science 2024-06-07 Ruohao Guo , Wei Xu , Alan Ritter

This work introduces a novel framework for evaluating LLMs' capacity to balance instruction-following with critical reasoning when presented with multiple-choice questions containing no valid answers. Through systematic evaluation across…

Computation and Language · Computer Science 2025-06-03 Gracjan Góral , Emilia Wiśnios , Piotr Sankowski , Paweł Budzianowski

Large language models (LLMs) often produce errors, including factual inaccuracies, biases, and reasoning failures, collectively referred to as "hallucinations". Recent studies have demonstrated that LLMs' internal states encode information…

Computation and Language · Computer Science 2025-05-20 Hadas Orgad , Michael Toker , Zorik Gekhman , Roi Reichart , Idan Szpektor , Hadas Kotek , Yonatan Belinkov

Pretrained Language Models (LMs) memorize a vast amount of knowledge during initial pretraining, including information that may violate the privacy of personal lives and identities. Previous work addressing privacy issues for language…

Computation and Language · Computer Science 2022-12-20 Joel Jang , Dongkeun Yoon , Sohee Yang , Sungmin Cha , Moontae Lee , Lajanugen Logeswaran , Minjoon Seo

Recent works have shown that Large Language Models (LLMs) have a tendency to memorize patterns and biases present in their training data, raising important questions about how such memorized content influences model behavior. One such…

Computation and Language · Computer Science 2025-07-01 Shanshan Xu , T. Y. S. S Santosh , Yanai Elazar , Quirin Vogel , Barbara Plank , Matthias Grabmair

Associative learning--forming links between co-occurring items--is fundamental to human cognition, reshaping internal representations in complex ways. Testing hypotheses on how representational changes occur in biological systems is…

Machine Learning · Computer Science 2025-10-27 Camila Kolling , Vy Ai Vo , Mariya Toneva

Large language models (LLMs) are trained on web-scale corpora that exhibit steep power-law distributions, in which the distribution of knowledge is highly long-tailed, with most appearing infrequently. While scaling has improved…

Computation and Language · Computer Science 2026-02-19 Sanket Badhe , Deep Shah , Nehal Kathrotia

Large language models (LLMs) exhibit cognitive biases -- systematic tendencies of irrational decision-making, similar to those seen in humans. Prior work has found that these biases vary across models and can be amplified by instruction…

Computation and Language · Computer Science 2025-07-15 Itay Itzhak , Yonatan Belinkov , Gabriel Stanovsky

The extraordinary success of recent Large Language Models (LLMs) on a diverse array of tasks has led to an explosion of scientific and philosophical theorizing aimed at explaining how they do what they do. Unfortunately, disagreement over…

Computation and Language · Computer Science 2026-05-04 Cameron Yetman

Scientific reasoning rarely stops at what is directly observable; it often requires uncovering hidden structure from data. From estimating reaction constants in chemistry to inferring demand elasticities in economics, this latent structure…

Artificial Intelligence · Computer Science 2026-05-01 Chaemin Jang , Woojin Park , Hyeok Yun , Dongman Lee , Jihee Kim

Reinforcement learning (RL)-based fine-tuning has become a crucial step in post-training language models for advanced mathematical reasoning and coding. Following the success of frontier reasoning models, recent work has demonstrated that…

Machine Learning · Computer Science 2025-08-11 Rosie Zhao , Alexandru Meterez , Sham Kakade , Cengiz Pehlevan , Samy Jelassi , Eran Malach

Though large language models (LLMs) have enabled great success across a wide variety of tasks, they still appear to fall short of one of the loftier goals of artificial intelligence research: creating an artificial system that can adapt its…

Computation and Language · Computer Science 2026-05-04 Michael A. Lepori , Tal Linzen , Ann Yuan , Katja Filippova

Research on Large Language Models (LLMs) increasingly focuses on identifying mechanistic explanations for their behaviors, yet the field lacks clear principles for determining when (and how) findings from one model instance generalize to…

Artificial Intelligence · Computer Science 2025-09-30 Sean Trott

Language models can store vast factual knowledge, yet their ability to flexibly use this knowledge for downstream tasks (e.g., via instruction finetuning) remains questionable. This paper investigates four fundamental knowledge manipulation…

Computation and Language · Computer Science 2024-07-17 Zeyuan Allen-Zhu , Yuanzhi Li

Large language models (LLMs) sometimes fail to respond appropriately to deterministic tasks -- such as counting or forming acronyms -- because the implicit prior distribution they have learned over sequences of tokens influences their…

Computation and Language · Computer Science 2025-04-18 Liyi Zhang , Veniamin Veselovsky , R. Thomas McCoy , Thomas L. Griffiths

The impressive capabilities of large language models (LLMs) have sparked debate over whether these models genuinely generalize to unseen tasks or predominantly rely on memorizing vast amounts of pretraining data. To explore this issue, we…

Computation and Language · Computer Science 2025-03-04 Xinyi Wang , Antonis Antoniades , Yanai Elazar , Alfonso Amayuelas , Alon Albalak , Kexun Zhang , William Yang Wang

Recent advancements in large language models (LLMs) have demonstrated emergent capabilities in complex reasoning, largely spurred by rule-based Reinforcement Learning (RL) techniques applied during the post-training. This has raised the…

Machine Learning · Computer Science 2025-07-22 Sneheel Sarangi , Hanan Salam

Large Language Models (LLMs) have impressive capabilities, but are prone to outputting falsehoods. Recent work has developed techniques for inferring whether a LLM is telling the truth by training probes on the LLM's internal activations.…

Artificial Intelligence · Computer Science 2024-08-20 Samuel Marks , Max Tegmark

Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks, yet they also exhibit memorization of their training data. This phenomenon raises critical questions about model behavior, privacy risks,…

Machine Learning · Computer Science 2025-12-15 Alexander Xiong , Xuandong Zhao , Aneesh Pappu , Dawn Song