English
Related papers

Related papers: Explorations of Self-Repair in Language Models

200 papers

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

Large Language Models (LLMs) achieve strong program repair performance but often suffer from over-editing, where excessive modifications overwrite correct code and hinder bug localization. We systematically quantify its impact and introduce…

Software Engineering · Computer Science 2026-04-08 Changxin Ke , Rui Zhang , Jiaming Guo , Yuanbo Wen , Li Ding , Shuo Wang , Xuyuan Zhu , Xiong Peng , Di Huang , Zidong Du , Xing Hu , Qi Guo , Yunji Chen

Large language models often reason beyond surface tokens, but the internal stage at which token-level information becomes abstract relational structure remains unclear. We investigate this question by analyzing how attention heads and…

Artificial Intelligence · Computer Science 2026-05-22 Junjie Zhang , Zhen Shen , Xisong Dong , Gang Xiong

Recent successes of reinforcement learning (RL) in training large reasoning models motivate the question of whether self-training - the process where a model learns from its own judgments - can be sustained within RL. In this work, we study…

Machine Learning · Computer Science 2025-10-10 Sheikh Shafayat , Fahim Tajwar , Ruslan Salakhutdinov , Jeff Schneider , Andrea Zanette

Transformer-based language models have achieved significant success; however, their internal mechanisms remain largely opaque due to the complexity of non-linear interactions and high-dimensional operations. While previous studies have…

Artificial Intelligence · Computer Science 2025-02-17 Lin Zhang , Lijie Hu , Di Wang

The performance of neural network models deteriorates due to their unreliable behavior on non-robust features of corrupted samples. Owing to their opaque nature, rectifying models to address this problem often necessitates arduous data…

Machine Learning · Computer Science 2026-03-18 Peiyu Yang , Naveed Akhtar , Jiantong Jiang , Ajmal Mian

Recently deep neural networks have been successfully used for various classification tasks, especially for problems with massive perfectly labeled training data. However, it is often costly to have large-scale credible labels in real-world…

Machine Learning · Computer Science 2019-01-15 Mingxiao An , Yongzhou Chen , Qi Liu , Chuanren Liu , Guangyi Lv , Fangzhao Wu , Jianhui Ma

Predicting upcoming events is critical to our ability to interact with our environment. Transformer models, trained on next-word prediction, appear to construct representations of linguistic input that can support diverse downstream tasks.…

Computation and Language · Computer Science 2023-11-10 Eghbal A. Hosseini , Evelina Fedorenko

Although substantial efforts have been made to mitigate catastrophic forgetting in continual learning, the intrinsic mechanisms are not well understood. In this work, we demonstrate the existence of "pseudo forgetting": the performance…

Machine Learning · Computer Science 2025-06-10 Huashan Sun , Yizhe Yang , Yinghao Li , Jiawei Li , Yang Gao

Large reasoning models (LRMs) have recently demonstrated impressive capabilities in complex reasoning tasks by leveraging increased test-time computation and exhibiting behaviors reminiscent of human-like self-reflection. While LRMs show a…

Computation and Language · Computer Science 2025-10-21 Qingcheng Zeng , Weihao Xuan , Leyang Cui , Rob Voigt

Transformer-based language models excel at both recall (retrieving memorized facts) and reasoning (performing multi-step inference), but whether these abilities rely on distinct internal mechanisms remains unclear. Distinguishing recall…

Machine Learning · Computer Science 2026-03-16 Harshwardhan Fartale , Ashish Kattamuri , Rahul Raja , Arpita Vats , Ishita Prasad , Akshata Kishore Moharir

Speech models have gained traction thanks to increase in accuracy from novel transformer architectures. While this impressive increase in performance across automatic speech recognition (ASR) benchmarks is noteworthy, there is still much…

Computation and Language · Computer Science 2024-09-06 Sai Gopinath , Joselyn Rodriguez

Recent large language models have demonstrated relevant capabilities in solving problems that require logical reasoning; however, the corresponding internal mechanisms remain largely unexplored. In this paper, we show that a small language…

Artificial Intelligence · Computer Science 2025-10-13 Davide Maltoni , Matteo Ferrara

Modern multilingual models are trained on concatenated text from multiple languages in hopes of conferring benefits to each (positive transfer), with the most pronounced benefits accruing to low-resource languages. However, recent work has…

Computation and Language · Computer Science 2020-10-08 Zirui Wang , Zachary C. Lipton , Yulia Tsvetkov

This work proposes a novel methodology for measuring compositional behavior in contemporary language embedding models. Specifically, we focus on adjectival modifier phenomena in adjective-noun phrases. In recent years, distributional…

Computation and Language · Computer Science 2024-12-19 Danilo S. Carvalho , Edoardo Manino , Julia Rozanova , Lucas Cordeiro , André Freitas

Autoregressive large language models (LLMs) compress knowledge from their training data through next-token conditional distributions. This limits tractable querying of this knowledge to start-to-end autoregressive sampling. However, many…

Machine Learning · Computer Science 2024-03-15 Edward J. Hu , Moksh Jain , Eric Elmoznino , Younesse Kaddar , Guillaume Lajoie , Yoshua Bengio , Nikolay Malkin

Reinforcement learning has become the dominant paradigm for eliciting reasoning and self-correction capabilities in large language models, but its computational expense motivates exploration of alternatives. Inspired by techniques from…

Artificial Intelligence · Computer Science 2025-12-03 David X. Wu , Shreyas Kapur , Anant Sahai , Stuart Russell

Reasoning models often generate long traces in which useful self-correction and unproductive revision are hard to distinguish. We study this distinction through backtracking dynamics: local reconsideration, retraction, or re-derivation…

Artificial Intelligence · Computer Science 2026-05-28 Navid Rezazadeh , Arash Gholami Davoodi

Mechanistic interpretability research seeks to reveal the inner workings of large language models, yet most work focuses on classification or generative tasks rather than summarization. This paper presents an interpretability framework for…

Computation and Language · Computer Science 2025-05-26 Anurag Mishra

A growing body of literature has focused on detailing the linguistic knowledge embedded in large, pretrained language models. Existing work has shown that non-linguistic biases in models can drive model behavior away from linguistic…

Computation and Language · Computer Science 2021-06-03 Forrest Davis , Marten van Schijndel