一作ACL 2026Findings· Findings of ACL
Intrinsic Mutual Information as a Modulator for Preference Optimization
Peng Liao · Peijia Zheng · Lingbo Li · Shangsong Liang · Lin Chen
摘要
Offline preference optimization methods, such as Direct Preference Optimization (DPO), offer significant advantages in aligning Large Language Models (LLMs) with human values. However, achieving optimal performance with these methods typically involves additional hyperparameter tuning, resulting...