Improving Preference Alignment of LLM with Inference-Free Self-Refinement

Large language models (LLMs) develop the incontext learning capability through pretraining and instruction tuning, enabling task adaptation without parameter updates. Self-refinement is a manifestation of this capability, which allows LLMs to iteratively refine the output using selfgenerated feedback. However, empirical observations reveal Inference-Free Self-Refinement (IFSR) in preference alignment: LLMs generate preference-improved output via fixed instructions, requiring no specific feedback, even no initial responses. There are two key components of the IFSR in preference alignment. The refining instruction is a fixed instruction that constrains the output distribution from a preference-semantic perspective. During training, it facilitates joint learning of preferencerelated semantic representations and data distribution alignment. The pseudo reference response is constructed from paired preference data and serves as a demonstration to guide the output distribution. It mitigates off-policy distributional bias while enhancing token-level preference learning in training. Experiments across multiple datasets demonstrate that incorporating IFSR into preference alignment yields performance improvement over 10%. Further ablation studies reveal additional characteristics and potential principles of IFSR.