一作ACL 2026Findings· Findings of ACL
B ias GRPO : Stabilizing Bias Mitigation in High-Variance Reward Landscapes via Group-Relative Policy Optimization
Saket Reddy · Ke Yang · ChengXiang Zhai
摘要
Mitigating social bias in Large Language Models (LLMs) presents a distinct alignment challenge: unlike verifiable tasks, social bias lacks a single ground truth, creating a high-variance, subjective reward landscape. Previous preference-based fine-tuning methods have major trade-offs: Direct Pref...