English
Related papers

Related papers: Erase to Improve: Erasable Reinforcement Learning …

200 papers

Despite the success of large language models (LLMs) in various natural language processing (NLP) tasks, the stored knowledge in these models may inevitably be incomplete, out-of-date, or incorrect. This motivates the need to utilize…

Computation and Language · Computer Science 2023-01-03 Hangfeng He , Hongming Zhang , Dan Roth

Reinforcement learning (RL) has been pivotal in enhancing the reasoning capabilities of large language models (LLMs), but it often suffers from limited exploration and entropy collapse, where models exploit a narrow set of solutions,…

Machine Learning · Computer Science 2025-10-20 Shijia Kang , Muhan Zhang

Large Language Models (LLMs) are increasingly adopted as evaluators, offering a scalable alternative to human annotation. However, existing supervised fine-tuning (SFT) approaches often fall short in domains that demand complex reasoning.…

Computation and Language · Computer Science 2025-11-04 Nuo Chen , Zhiyuan Hu , Qingyun Zou , Jiaying Wu , Qian Wang , Bryan Hooi , Bingsheng He

Large Language Models (LLMs) are smart but forgetful. Recent studies, (e.g., (Bubeck et al., 2023)) on modern LLMs have shown that they are capable of performing amazing tasks typically necessitating human-level intelligence. However,…

Computation and Language · Computer Science 2023-11-08 Eric Melz

Reinforcement learning plays a crucial role in generative re-ranking scenarios due to its exploration-exploitation capabilities, but existing generative methods mostly fail to adapt to the dynamic entropy changes in model difficulty during…

Artificial Intelligence · Computer Science 2026-01-21 Changshuo Zhang

Large Language Models (LLMs) are powerful reasoners in natural language, but their actions are typically confined to outputting vocabulary tokens. As a result, interactions with external environments -- such as symbolic operators or…

Machine Learning · Computer Science 2025-10-20 Zhongqi Yue , Weishi Wang , Yundaichuan Zhan , Juncheng Li , Daniel Dahlmeier , Fredrik D. Johansson

Large Language Models (LLMs) excel in many areas but continue to face challenges with complex reasoning tasks, such as Multi-Hop Question Answering (MHQA). MHQA requires integrating evidence from diverse sources while managing intricate…

Computation and Language · Computer Science 2025-05-29 Bolei He , Xinran He , Mengke Chen , Xianwei Xue , Ying Zhu , Zhenhua Ling

Retrieval-augmented generation (RAG) has been widely adopted to ground large language models (LLMs) in external knowledge, yet it remains largely underexplored for improving reasoning. Existing methods either rely on online exploration…

Artificial Intelligence · Computer Science 2026-02-10 Jiaxiang Chen , Zhuo Wang , Mingxi Zou , Qifan Wang , Zenglin Xu

Reinforcement learning (RL) is a machine learning approach that trains agents to maximize cumulative rewards through interactions with environments. The integration of RL with deep learning has recently resulted in impressive achievements…

Neural and Evolutionary Computing · Computer Science 2023-08-31 Hui Bai , Ran Cheng , Yaochu Jin

Reinforcement learning has been shown to improve the performance of large language models. However, traditional approaches like RLHF or RLAIF treat the problem as single-step. As focus shifts toward more complex reasoning and agentic tasks,…

Artificial Intelligence · Computer Science 2025-04-29 Anna Goldie , Azalia Mirhoseini , Hao Zhou , Irene Cai , Christopher D. Manning

Recent advances in reasoning-centric language models have highlighted reinforcement learning (RL) as a promising method for aligning models with verifiable rewards. However, it remains contentious whether RL truly expands a model's…

Computation and Language · Computer Science 2025-06-02 Mingjie Liu , Shizhe Diao , Ximing Lu , Jian Hu , Xin Dong , Yejin Choi , Jan Kautz , Yi Dong

Elucidating the reasoning process with structured explanations from question to answer is crucial, as it significantly enhances the interpretability, traceability, and trustworthiness of question-answering (QA) systems. However, structured…

Computation and Language · Computer Science 2024-09-30 Guoxin Chen , Kexin Tang , Chao Yang , Fuying Ye , Yu Qiao , Yiming Qian

Reinforcement Learning with Verifiable Rewards(RLVR) has demonstrated great potential in enhancing the reasoning capabilities of large language models (LLMs). However, its success has thus far been largely confined to the mathematical and…

Artificial Intelligence · Computer Science 2026-02-05 Mengyu Zhang , Siyu Ding , Weichong Yin , Yu Sun , Hua Wu

Large vision-language models (VLMs) fine-tuned on specialized visual instruction-following data have exhibited impressive language reasoning capabilities across various scenarios. However, this fine-tuning paradigm may not be able to…

Artificial Intelligence · Computer Science 2024-10-10 Yuexiang Zhai , Hao Bai , Zipeng Lin , Jiayi Pan , Shengbang Tong , Yifei Zhou , Alane Suhr , Saining Xie , Yann LeCun , Yi Ma , Sergey Levine

Teaching large language models (LLMs) to reason during post-training typically relies on reinforcement learning with explicit outcome- or process-based reward functions. However, in many real-world settings, obtaining or defining such…

Artificial Intelligence · Computer Science 2026-05-19 Claudio Fanconi , Nicolás Astorga , Mihaela van der Schaar

Large Reasoning Models (LRMs) have shown remarkable capabilities in solving complex problems through reinforcement learning (RL), particularly by generating long reasoning traces. However, these extended outputs often exhibit substantial…

Computation and Language · Computer Science 2025-05-22 Wei Liu , Ruochen Zhou , Yiyun Deng , Yuzhen Huang , Junteng Liu , Yuntian Deng , Yizhe Zhang , Junxian He

When the world changes, so does the text that humans write about it. How do we build language models that can be easily updated to reflect these changes? One popular approach is retrieval-augmented generation, in which new documents are…

Computation and Language · Computer Science 2024-06-18 Belinda Z. Li , Emmy Liu , Alexis Ross , Abbas Zeitoun , Graham Neubig , Jacob Andreas

Large Language Models (LLMs) have shown strong capabilities through two complementary paradigms: Retrieval-Augmented Generation (RAG) for knowledge grounding and Reinforcement Learning from Verifiable Rewards (RLVR) for complex reasoning.…

Computation and Language · Computer Science 2026-04-27 Weitao Li , Boran Xiang , Xiaolong Wang , Zhinan Gou , Weizhi Ma , Yang Liu

Although Retrieval-Augmented Large Language Models (RALMs) demonstrate their superiority in terms of factuality, they do not consistently outperform the original retrieval-free Language Models (LMs). Our experiments reveal that this…

Artificial Intelligence · Computer Science 2025-03-07 Mingda Li , Xinyu Li , Yifan Chen , Wenfeng Xuan , Weinan Zhang

Improving the reasoning capabilities of large language models (LLMs) typically relies either on the model's ability to sample a correct solution to be reinforced or on the existence of a stronger model able to solve the problem. However,…

Machine Learning · Computer Science 2026-02-03 Ethan Mendes , Jungsoo Park , Alan Ritter