RL for Language Models

RL: Reinforcement Learning

Follow this topic Ask about this topic

Momentum

36 papers in the last four weeks, up 71% on the four weeks before. 0.4% of all new papers.

Jul 13Week of Sep 28

Latest papers 271

All topics

Improving Cross-Lingual Factual Recall via Consistency-Driven Reinforcement Learning
Jun 4, 2026Jonathan von Rad, Louis Arts, George Burgess +6Multilingual Language Model Evaluation RL for Language Models
University College London, Centre for Artificial Intelligence
Reinforcement Learning Elicits Contextual Learning of Unseen Language Translation
Jun 4, 2026Hanxu Hu, Zdeněk Šnajdr, Pinzhen Chen +2RL for Language Models In-Context Learning
University of Zurich · ETH Zurich · Queen’s University Belfast
When AI Says It Feels
Jun 4, 2026Shin-nosuke Ishikawa, Seiya Ikeda, Hirotsugu OhbaRL for Language Models
Graduate School of Artificial Intelligence and Science, Rikkyo University · AI Technical Sector, Mamezo Co., Ltd. · AI Consulting Division, Mamezo Co., Ltd.
SHALA-LLM: Smartly Handling Ambiguous Labels in Aligning LLMs
Jun 3, 2026Jingyao Wu, Ashley Wang, Keane Ong +2RL for Language Models LLM Alignment
MIT Media Lab, Massachusetts Institute of Technology · National University of Singapore
Alpha-RTL: Test-Time Training for RTL Hardware Optimization
Jun 3, 2026Peilong Zhou, Zhirong Chen, Cangyuan Li +4RL for Language Models Test-Time Optimization
1SKLP, Institute of Computing Technology, Chinese Academy of Sciences · University of the Chinese Academy of Sciences · School of Advanced Interdisciplinary Sciences
Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning
Jun 3, 2026Xuekang Wang, Zhuoyuan Hao, Shuo Hou +3Reward Hacking RL for Language Models
Tsinghua University · Harbin Institute of Technology, Shenzhen · Xi’an Jiaotong University
BiasGRPO: Stabilizing Bias Mitigation in High-Variance Reward Landscapes via Group-Relative Policy Optimization
Jun 3, 2026Saket Reddy, Ke Yang, ChengXiang ZhaiReward Modeling RL for Language Models
University of Illinois - Urbana-Champaign
RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training
Jun 2, 2026Rachit Bansal, Clara Mohri, Tian Qin +2Language Model Pretraining Supervised Fine-Tuning
Harvard University
Taiji: Pareto Optimal Policy Optimization with Semantics-IDs Trade-off for Industrial LLM-Enhanced Recommendation
Jun 2, 2026Yuecheng Li, Zeyu Song, Jing Yao +3RL for Language Models Large Language Model-Based Recommendation
Kuaishou Technology Beijing, China · Unaffiliated Beijing, China
Large Language Models Hack Rewards, and Society
Jun 2, 2026Wei Liu, Xinyi Mou, Hanqi Yan +2Reward Hacking RL for Language Models
King’s College London · Fudan University · Shanghai Innovation Institute +1
Mitigating False Credit Propagation: Probabilistic Graphical Reward Aggregation for Rubric-Based Reinforcement Learning
Jun 2, 2026Can Lv, Mingju Chen, Heng Chang +1Reward Modeling RL for Language Models
Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing, School of Artificial Intelligence, Beihang University · Tsinghua University
Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning
Jun 2, 2026Yanyu Zhu, Hoilam Pao, Niu Hu +6RL for Language Models Speculative Decoding
1Tsinghua Shenzhen International Graduate School · 3Huawei Noah’s Ark Lab · 4Northwestern Polytechnical University +1
Efficient Hyperparameter Optimization for LLM Reinforcement Learning
Jun 2, 2026Minping Chen, Bowen Xiao, Du Liang +2RL for Language Models RL Post-Training
1The Hong Kong University of Science and Technology (Guangzhou) · 3China United Network Communications Group · 2The Hong Kong University of Science and Technology
A Local Perturbation Theory for Cross-Domain Interference and Recovery in Multi-Domain RL
Jun 1, 2026Lei Yang, Siyu Ding, Deyi XiongRL for Language Models Reinforcement Learning
TJUNLP Lab, College of Intelligence and Computing, Tianjin University, Tianjin, China · Baidu Inc., Beijing, China
AgentPLM: Agentic Protein Language Models with Reasoning-Augmented Decoding for Protein Sequence Design
Jun 1, 2026Sahil Rahman, Maxx Richard RahmanRL for Language Models Direct Preference Optimization
Bedford College, London, United Kingdom · Saarland University, Saarbrücken, Germany
LEAF: Growing Trees Without Branching for Speech-Aware Large Language Model Post-Training
May 29, 2026Argyrios Gerogiannis, Yekaterina Yegorova, Mark Hasegawa-Johnson +1RL for Language Models Credit Assignment in RL
University of Illinois, Urbana-Champaign
DRIFT: Decoupled Rollouts and Importance-Weighted Fine-Tuning for Efficient Multi-Turn Optimization
May 29, 2026Jian Mu, Tianyi Lin, Chengwei Qin +2Supervised Fine-Tuning RL for Language Models
The Hong Kong University of Science and Technology (Guangzhou) · The Chinese University of Hong Kong, Shenzhen.
Reinforcement Learning Can Amplify Emergent Misalignment from Harmless Rewards
May 29, 2026Magnus Jørgenvåg, David Kaczér, Lasse Ruttert +3RL for Language Models LLM Alignment
Bonn-Aachen International Center for Information Technology, University of Bonn, Germany · Lamarr Institute for Machine Learning and Artificial Intelligence, Germany
DARTS: Distribution-Aware Active Rollout Trajectory Shaping for Accelerating LLM Reinforcement Learning
May 29, 2026Yujie Wang, Siwei Chen, Longzan Luo +4RL for Language Models Reinforcement Learning
School of Computer Science & Beijing Key Laboratory of Software and Hardware Cooperative Artificial Intelligence Systems, Peking University, Beijing, China · School of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China · Institute of Computational Social Science, Peking University (Qingdao), Qingdao, China
How's it going? Reinforcement learning in language models recruits a functional welfare axis
May 28, 2026Andy Q Han, David J. Chalmers, Pavel IzmailovRL for Language Models RL Post-Training
New York University
RL2ML: Finite-Rollout Surrogate Objectives from Reinforcement Learning to Maximum Likelihood
May 28, 2026Yifu ZhengRL for Language Models Policy Gradient
University of Southern California
EvoRubric: Self-Evolving Rubric-Driven RL for Open-Ended Generation
May 28, 2026Xin Guan, Xiaomeng Hu, Shen Huang +6Open-Ended Generation RL for Language Models
Tongyi Lab, Alibaba Group
Hista and Numca: Estimate State Value Effectively for LLM Reinforcement Learning
May 28, 2026Zizhe Chen, Jiqian Dong, Yizhou Tian +4RL for Language Models Value Function Estimation
Department of Computer Science and Engineering, The Chinese University of Hong Kong · Huawei Technologies Ltd.
LiteCoder-Terminal: Scaling Long-Horizon Terminal Environments for Learning Language Agents
May 28, 2026Xiaoxuan Peng, Kaiqi Zhang, Xinyu Lu +5RL for Language Models Terminal Agents
Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences · University of Chinese Academy of Sciences
Source-Grounded Semantic Reinforcement Learning for Low-Resource Target-Language Generation
May 28, 2026Zeli Su, Ziyin Zhang, Zewei Pan +8RL for Language Models Low-Resource Language Processing
Minzu University of China · Shanghai Jiao Tong University · Peking University +3
When RL Suppresses Its Own Vocabulary: Recovering Reasoning Diversity in Puzzle-to-Math Transfer
May 28, 2026Mayug Maniparambil, Arjun Karuvally, Terrence Sejnowski +1RL for Language Models RL for Language Model Reasoning
Fin AI Research · Salk Institute for Biological Studies
RUBRIC-ARROW: Alternating Pointwise Rubric Reward Modeling for LLM Post-training in Non-verifiable Domains
May 27, 2026Haoxiang Jiang, Zihan Dong, Tianci Liu +5Reward Modeling RL for Language Models
University at Albany · 2Rutgers University · 3Purdue University +3
Long Live The Balance: Information Bottleneck Driven Tree-based Policy Optimization
May 27, 2026Hao Jiang, Shurui Li, Tianpeng Bu +7RL for Language Models Exploration-Exploitation Tradeoff
Alibaba Cloud Computing, Alibaba Group.
Reward Bias Substitution: Single-Axis Bias Mitigations Redirect Optimization Pressure
May 27, 2026Max Lamparth, Daniel Fein, Andreas Haupt +2Reward Modeling RL for Language Models
Stanford University · University of Pennsylvania
EAPO: Entropy-Driven Adaptive Positive-Negative Sample Weighting for Policy Optimization in Open-Ended QA
May 27, 2026Yunsheng Zeng, Gen Li, Yuwei Miao +8RL for Language Models Reinforcement Learning with Verifiable Rewards
1Baidu Inc.

Jun 4, 2026, cs.CLJ/K move · Enter open · S save

Improving Cross-Lingual Factual Recall via Consistency-Driven Reinforcement Learning

Jonathan von Rad, Louis Arts, George Burgess, Eleftheria Kolokytha+5

University College London, Centre for Artificial Intelligence

Multilingual Language Model Evaluation RL for Language Models Factual Consistency Evaluation Multilingual QA Factual Knowledge in Language Models Cross-Lingual Consistency in Language Models+1

Open paper AskPDF arXiv

Large language models (LLMs) trained predominantly on English data encode substantial world knowledge, yet often fail to express it reliably in other languages, a phenomenon known as cross-lingual factual inconsistency. To study and address this, we introduce PolyFact, a large-scale parallel multilingual factual QA dataset containing 100K Wikidata-grounded facts across 12 typologically diverse languages. Using PolyFact, we compare light continual pretraining (CPT), supervised fine-tuning (SFT), and reinforcement learning via Group Relative Policy Optimization (GRPO) for improving cross-lingual factual recall in Qwen-2.5-7B and OLMo-2-1124-7B. We find that GRPO consistently outperforms SFT, improving both cross-lingual consistency and generalization to unseen languages, while CPT on parallel data yields limited additional gains. Mechanistic analyses further show that GRPO reorganizes multilingual routing by reducing language specialization in MLP layers and attention heads, thereby promoting more shared cross-lingual representations. We release our code, models, and dataset.

Momentum

Related topics

Latest papers 271