4 papers
VI-CuRL: Stabilizing Verifier-Independent RL Reasoning via Confidence-Guided Variance Reduction
Xin-Qiang Cai, Masashi Sugiyama
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a dominant paradigm for enhancing Large Language Models (LLMs) reasoning, yet its reliance on external verifier…
Positive-Unlabeled Reinforcement Learning Distillation for On-Premise Small Models
Zhiqiang Kou, Junyang Chen, Xin-Qiang Cai +8
Due to constraints on privacy, cost, and latency, on-premise deployment of small models is increasingly common. However, most practical pipelines stop at supervised fine-tuning (SF…
Rethinking Toxicity Evaluation in Large Language Models: A Multi-Label Perspective
Zhiqiang Kou, Junyang Chen, Xin-Qiang Cai +8
Large language models (LLMs) have achieved impressive results across a range of natural language processing tasks, but their potential to generate harmful content has raised seriou…
Offline Reinforcement Learning with Domain-Unlabeled Data
Soichiro Nishimori, Xin-Qiang Cai, Johannes Ackermann +1
Offline reinforcement learning (RL) is vital in areas where active data collection is expensive or infeasible, such as robotics or healthcare. In the real world, offline datasets o…