Mitigating social bias in Large Language Models (LLMs) presents a distinct alignment challenge: unlike verifiable tasks, bias lacks a single ground truth, creating a high-variance, subjective reward landscape. Previous preference-based fine-tuning methods have major trade-offs: Direct Preference Optimization (DPO) is limited by the lack of exploration inherent in offline training, while Proximal Policy Optimization (PPO) can lead to training instability due to potentially unreliable critic estimates.
arXiv:2608. 00175v1 Announce Type: new Abstract: Deep reinforcement learning (RL) agents achieve strong performance by optimizing scalar reward functions.
By Umer Siddique, Peilang Li, Conor Wallace, Yongcan Cao
arXiv:2607. 03248v1 Announce Type: cross Abstract: The alignment of large language models with human preferences is commonly achieved through Reinforcement Learning from Human Feedback or Direct Preference Optimization.
By Jialiang Wang, Xianming Liu, Xiong Zhou, Hui Liu, Haoliang Li
arXiv:2606. 04807v1 Announce Type: new Abstract: Mitigating social bias in Large Language Models (LLMs) presents a distinct alignment challenge: unlike verifiable tasks, bias lacks a single ground truth, creating a high-variance, subjective reward landscape.
By Saket Reddy, Ke Yang, ChengXiang Zhai
arXiv:2607. 20515v1 Announce Type: new Abstract: Reinforcement Learning from Human Feedback (RLHF) is critical for aligning Large Language Models (LLMs) with human preferences.
By Jingyi Huang, Ruohan Zong, Yujun Feng, Liran Ma, Lanyu Shang, Yang Zhang
arXiv:2504. 06659v2 Announce Type: replace-cross Abstract: Despite advances in Preference Alignment (PA) for Large Language Models (LLMs), mainstream methods like reinforcement learning with human feedback face notable challenges.
By Xiaohua Feng, Yuyuan Li, Huwei Ji, Jiaming Zhang, Li Zhang, Tianyu Du, Chaochao Chen