arXiv Machine Learning

An Empirical Study of Reward Specification and Benchmark Reliability in GRPO-based LLM Unlearning

arXiv:2608. 17804v1 Announce Type: new Abstract: Practical LLM unlearning is usually evaluated through two objectives: suppress target-specific knowledge and preserve non-target utility.

arXiv AI

1d ago

Measuring Reward Hacking and Reasoning-Answer Decoupling Under Position-Confounded Optimization

arXiv:2608. 15445v1 Announce Type: new Abstract: When a reward is correct on every training example yet consistent with more than one goal, a model can acquire an unintended one, a failure known as goal misgeneralization.

By Suyash Maniyar, Armaan Sandhu, Abhishek Mishra

llms benchmarks

arXiv AI

Aug 11

Search-G1: Grounded Search Agents via Representation-Based Intrinsic Rewards

arXiv:2608. 07531v1 Announce Type: cross Abstract: Search-augmented language agents should retrieve external information only when necessary and ground their answers in retrieved evidence.

By Cheng Ruoxi, Ma Haoxuan, Zhang Hongyi, Zhang Junming, Duan Ranjie, Xia Qiaolin, Wang Hao, Lu Yu, Shi Haibo, Ma Xingjun

llms agents reinforcement-learning benchmarks

arXiv AI

Jun 10

TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning

arXiv:2509. 25760v2 Announce Type: replace-cross Abstract: While large language models (LLMs) have demonstrated strong performance on factoid question answering, they are still prone to hallucination and untruthful responses, particularly when tasks demand information outside their parametric knowledge.

By Zhepei Wei, Xiao Yang, Kai Sun, Jiaqi Wang, Rulin Shao, Jingxiang Chen, Mohammad Kachuee, Teja Gollapudi, Yiwei Liao, Nicolas Scheffer, Rakesh Wanga, Anuj Kumar, Yu Meng, Wen-tau Yih, Xin Luna Dong

llms nlp reinforcement-learning benchmarks safety

arXiv Machine Learning

Jun 26

Designing Reward Signals for Portable Query Generation: A Case Study in Industrial Semantic Job Search

arXiv:2606. 27291v1 Announce Type: new Abstract: Job-search platforms rely on low-bandwidth query interfaces that often fail to capture the high-dimensional complexity of candidate profiles.

By Ping Liu, Qianqi Shen, Jianqiang Shen, Wenqiong Liu, Rajat Arora, Yunxiang Ren, Chunnan Yao, Dan Xu, Baofen Zheng, Wanjun Jiang, Andrii Soviak, Kevin Kao, Jingwei Wu, Wenjing Zhang

llms reinforcement-learning safety

arXiv AI

Jul 23

Reinforcement Learning for Large Language Model Selective Evidence Adoption from Contaminated Retrieval Results

arXiv:2607. 20090v1 Announce Type: cross Abstract: Retrieval-augmented large language models frequently face contexts that interleave useful evidence with misleading statements or instruction-like content.

By Yanyu Chen, Yue Li, Yongyi Cui, Dongsheng Shi, Lichang Dai

llms rag reinforcement-learning benchmarks

arXiv AI

Aug 12

Evaluation-Conditioned Training: Teaching Models to Generalize to Stronger Oversight Regimes

arXiv:2608. 10209v1 Announce Type: new Abstract: Feedback signals used to train Large Language Models (LLMs) are the primary driver of their behavior and our main lever for instilling alignment with human values and objectives.

By Alec Harris, Kasey Corra, Archie Chaudhury, Yixiong Hao

llms reinforcement-learning fine-tuning safety

arXiv Machine Learning

Jul 31

HARGO: Heterogeneity-Aware Reward-Guided Optimization for RL Post-Training of LLMs on HPC Tasks

arXiv:2607. 28301v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) can equip large language models (LLMs) with domain knowledge for high-performance computing (HPC) tasks such as data race detection and benchmark question answering.

By Tiangang Li, Xiangbo Tian

llms nlp reinforcement-learning fine-tuning benchmarks safety

arXiv Machine Learning

Jul 7

Reward Granularity in RLVR: Comparing Process and Outcome Reward Structures for Mathematical Reasoning in Small Language Models

arXiv:2607. 02869v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising paradigm for improving mathematical reasoning in language models.

By Anagha Radhakrishna Palandye, Rebecca Glick, Osheen Kaul

llms reinforcement-learning fine-tuning

arXiv AI

Jul 29

CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimization

arXiv:2607. 25659v1 Announce Type: new Abstract: Rubric-based reinforcement learning enriches language model training by evaluating model outputs against explicit criteria.

By Bo-Wen Zhang, Junwei He, Wen Wang, Song-Lin Lv, Wentao Ma, Rongyi Lin, Shuhan Zhong, Lan-Zhe Guo

llms reinforcement-learning

arXiv AI

Jul 8

Improving LLM-Generated Process Model Quality Through Reinforcement Learning: The Role of Reward Function Design

arXiv:2607. 06175v1 Announce Type: cross Abstract: Large language models (LLMs) can generate BPMN process models from natural-language descriptions, yet supervised fine-tuning (SFT) limits their output quality to the patterns present in the training data.

By Alexander Rombach, Chantale Lauer, Nijat Mehdiyev

llms reinforcement-learning fine-tuning

Hugging Face Trending Papers

Jun 25

Designing Reward Signals for Portable Query Generation: A Case Study in Industrial Semantic Job Search

Job-search platforms rely on low-bandwidth query interfaces that often fail to capture the high-dimensional complexity of candidate profiles. We present an end-to-end RLAIF (Reinforcement Learning from AI Feedback) framework to generate \emph{portable} job search queries, terms that abstract away seeker-specific identifiers while preserving generalizable qualifications.

llms reinforcement-learning safety

arXiv AI

Jul 28

Beyond Direct Answering: Aligning Educational LLMs as Socratic Guides via Heuristic Reinforcement Learning

arXiv:2607. 22996v1 Announce Type: cross Abstract: Large language models (LLMs) deployed in educational settings often behave as direct answerers: they disclose target concepts in the opening turn instead of guiding students through progressive inquiry, as Socratic pedagogy prescribes.

By Xiaokun Wang, Siyu Song, Wentao Liu, Xiaodong Zou

llms reinforcement-learning safety

Related stories