paper-with-me

홈 › Papers

ARF-RLHF: Adaptive Reward-Following for RLHF through Emotion-Driven Self-Supervision and Trace-Biased Dynamic Optimization

2025-07-03 · YuXuan Zhang arxiv

Current RLHF methods such as PPO and DPO typically reduce human preferences to binary labels, which are costly to obtain and too coarse to reflect individual variation. We observe that expressions of satisfaction and dissatisfaction follow stable linguistic patterns across users, indicating that more informative supervisory signals can be extracted from free-form feedback. Building on this insight, we introduce Adaptive Reward-Following (ARF), which converts natural feedback into continuous preference trajectories and optimizes them using the novel TraceBias algorithm. Across diverse LLMs and preference domains, ARF consistently outperforms PPO and DPO, improving alignment by up to 7.6%. Our results demonstrate that continuous reward modeling provides a scalable path toward personalized and theoretically grounded RLHF.

📄 PDF Abstract BibTeX arXiv:2507.03069

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Curiosity-Driven Reinforcement Learning from Human Feedback

2025-01-20 · Haoran Sun, Yekun Chai, Shuohuan Wang, Yu Sun 외

Reinforcement learning from human feedback (RLHF) has proven effective in aligning large language models (LLMs) with human preferences, but often at the cost of reduced output diversity. This trade-off between diversity …

DiversityInstruction Followingreinforcement-learningReinforcement Learning+1

The Perfect Blend: Redefining RLHF with Mixture of Judges

2024-09-30 · Tengyu Xu, Eryk Helenowski, Karthik Abinav Sankararaman, Di Jin 외

Reinforcement learning from human feedback (RLHF) has become the leading approach for fine-tuning large language models (LLM). However, RLHF has limitations in multi-task learning (MTL) due to challenges of reward hackin…

Instruction FollowingMathMulti-Task Learning

SharedRep-RLHF: A Shared Representation Approach to RLHF with Diverse Preferences

2025-09-03 · Arpan Mukherjee, Marcello Bullo, Deniz Gündüz arxiv

Uniform-reward reinforcement learning from human feedback (RLHF), which trains a single reward model to represent the preferences of all annotators, fails to capture the diversity of opinions across sub-populations, inad…

Reinforcement Learning

Adaptive Dense Reward: Understanding the Gap Between Action and Reward Space in Alignment

2024-10-23 · Yanshi Li, Shaopan Xiong, Gengru Chen, Xiaoyang Li 외

Reinforcement Learning from Human Feedback (RLHF) has proven highly effective in aligning Large Language Models (LLMs) with human preferences. However, the original RLHF typically optimizes under an overall reward, which…

GSM8KHumanEvalMMLU

Reinforcement Learning from Human Feedback: A Statistical Perspective

2026-04-02 · Pangpang Liu, Chengchun Shi, Will Wei Sun arxiv

Reinforcement learning from human feedback (RLHF) has emerged as a central framework for aligning large language models (LLMs) with human preferences. Despite its practical success, RLHF raises fundamental statistical qu…

Reinforcement LearningActive Learning