English
Related papers

Related papers: Reinforcement Learning with Token-level Feedback f…

200 papers

Reinforcement learning (RL) has become a central paradigm for post-training large language models (LLMs), particularly for complex reasoning tasks, yet it often suffers from exploration collapse: policies prematurely concentrate on a small…

Machine Learning · Computer Science 2026-01-16 Zhiyuan Hu , Yucheng Wang , Yufei He , Jiaying Wu , Yilun Zhao , See-Kiong Ng , Cynthia Breazeal , Anh Tuan Luu , Hae Won Park , Bryan Hooi

Large language models (LLMs) often solve challenging math exercises yet fail to apply the concept right when the problem requires genuine understanding. Popular Reinforcement Learning with Verifiable Rewards (RLVR) pipelines reinforce final…

Artificial Intelligence · Computer Science 2026-05-08 Zijun Gao , Zhikun Xu , Xiao Ye , Ben Zhou

Large Language Models (LLMs) have shown significant potential in designing reward functions for Reinforcement Learning (RL) tasks. However, obtaining high-quality reward code often involves human intervention, numerous LLM queries, or…

Machine Learning · Computer Science 2024-10-21 Shengjie Sun , Runze Liu , Jiafei Lyu , Jing-Wen Yang , Liangpeng Zhang , Xiu Li

We propose reinforcement learning (RL) strategies tailored for reasoning in large language models (LLMs) under strict memory and compute limits, with a particular focus on compatibility with LoRA fine-tuning. Building on early policy…

Machine Learning · Computer Science 2025-06-13 Alan Lee , Harry Tong

Existing reinforcement learning strategies based on outcome supervision have proven effective in enhancing the performance of large language models(LLMs) for code generation. While reinforcement learning based on process supervision has…

Software Engineering · Computer Science 2025-02-05 Yufan Ye , Ting Zhang , Wenbin Jiang , Hua Huang

Rubric-based Reinforcement Learning (RL) has emerged as a promising approach for aligning Large Language Models (LLMs) with complex, open-domain instruction following tasks. However, existing methods predominantly rely on response-level…

This paper investigates Reinforcement Learning (RL) on data without explicit labels for reasoning tasks in Large Language Models (LLMs). The core challenge of the problem is reward estimation during inference while not having access to…

The development of Large Language Models (LLMs) often confronts challenges stemming from the heavy reliance on human annotators in the reinforcement learning with human feedback (RLHF) framework, or the frequent and costly external queries…

Computation and Language · Computer Science 2025-03-04 Shangding Gu , Alois Knoll , Ming Jin

Considering a collection of RDF triples, the RDF-to-text generation task aims to generate a text description. Most previous methods solve this task using a sequence-to-sequence model or using a graph-based model to encode RDF triples and to…

Computation and Language · Computer Science 2022-03-24 Hanning Gao , Lingfei Wu , Hongyun Zhang , Zhihua Wei , Po Hu , Fangli Xu , Bo Long

Post-training with Reinforcement Learning (RL) has substantially improved reasoning in Large Language Models (LLMs) via test-time scaling. However, extending this paradigm to Multimodal LLMs (MLLMs) through verbose rationales yields limited…

Computation and Language · Computer Science 2026-02-16 Bangzheng Li , Jianmo Ni , Chen Qu , Ian Miao , Liu Yang , Xingyu Fu , Muhao Chen , Derek Zhiyuan Cheng

Reinforcement learning (RL) commonly relies on scalar rewards with limited ability to express temporal, conditional, or safety-critical goals, and can lead to reward hacking. Temporal logic expressible via the more general class of…

Artificial Intelligence · Computer Science 2025-11-26 Dominik Wagner , Leon Witzman , Luke Ong

Watermarking has emerged as a promising solution for tracing and authenticating text generated by large language models (LLMs). A common approach to LLM watermarking is to construct a green/red token list and assign higher or lower…

Cryptography and Security · Computer Science 2025-10-27 Li An , Yujian Liu , Yepeng Liu , Yuheng Bu , Yang Zhang , Shiyu Chang

Long chain-of-thought (CoT) significantly enhances the reasoning capabilities of large language models (LLMs). However, extensive reasoning traces lead to inefficiencies and increased time-to-first-token (TTFT). We propose a training…

Computation and Language · Computer Science 2026-01-08 Roy Xie , David Qiu , Deepak Gopinath , Dong Lin , Yanchao Sun , Chong Wang , Saloni Potdar , Bhuwan Dhingra

Much literature has shown that prompt-based learning is an efficient method to make use of the large pre-trained language model. Recent works also exhibit the possibility of steering a chatbot's output by plugging in an appropriate prompt.…

Computation and Language · Computer Science 2022-10-14 Hsuan Su , Pohan Chi , Shih-Cheng Huang , Chung Ho Lam , Saurav Sahay , Shang-Tse Chen , Hung-yi Lee

Recent advances have demonstrated the effectiveness of Reinforcement Learning (RL) in improving the reasoning capabilities of Large Language Models (LLMs). However, existing works inevitably rely on high-quality instructions and verifiable…

Computation and Language · Computer Science 2026-01-27 Wenkai Fang , Shunyu Liu , Yang Zhou , Kongcheng Zhang , Tongya Zheng , Kaixuan Chen , Mingli Song , Dacheng Tao

Next-token prediction is the fundamental principle for training large language models (LLMs), and reinforcement learning (RL) further enhances their reasoning performance. As an effective way to model language, image, video, and other…

Computer Vision and Pattern Recognition · Computer Science 2025-05-27 Zuyao Chen , Jinlin Wu , Zhen Lei , Marc Pollefeys , Chang Wen Chen

Large language models handle single-turn generation well, but multi-turn interactions still require the model to reconstruct user intent and task state from an expanding token history because internal representations do not persist across…

Computation and Language · Computer Science 2025-12-11 Vishwas Hegde , Vindhya Shigehalli

Reinforcement Learning (RL) has proven to be an effective post-training strategy for enhancing reasoning in vision-language models (VLMs). Group Relative Policy Optimization (GRPO) is a recent prominent method that encourages models to…

Artificial Intelligence · Computer Science 2025-10-30 Jiaqi Wang , Kevin Qinghong Lin , James Cheng , Mike Zheng Shou

Test-time scaling methods have seen a rapid increase in popularity for its computational efficiency and parameter-independent training to improve reasoning performance on Large Language Models. One such method is called budget forcing, a…

Artificial Intelligence · Computer Science 2025-10-27 Ravindra Aribowo Tarunokusumo , Rafael Fernandes Cunha

We tackle the problem of aligning pre-trained large language models (LMs) with human preferences. If we view text generation as a sequential decision-making problem, reinforcement learning (RL) appears to be a natural conceptual framework.…