On-Policy Self-Alignment with Fine-grained Knowledge Feedback for Hallucination Mitigation

Understand

Hallucination occurs when large language models exhibit behavior that deviates from the boundaries of their knowledge during response generation.

• To address this critical issue, previous learning-based methods attempt to finetune models but are limited by off-policy sampling and coarse-grained feedback.
• In this paper, we present \textit{\b{R}einforcement \b{L}earning \b{f}or \b{H}allucination} (RLFH), an on-policy self-alignment approach that enables LLMs to actively explore their knowledge boundaries and self-correct generation behavior through fine-grained feedback signals.
• RLFH introduces a self-assessment framework where the policy serves as its own judge.