Iterative Critique-Refine Framework for Enhancing LLM Personalization

arXiv:2510.24469v2 Announce Type: replace-cross Abstract: Personalized text generation requires models not only to produce coherent text but also to align with a target user's style, tone, and topical focus. Existing retrieval-augmented approaches such as LaMP and PGraphRAG enrich profiles with user and neighbor histories, but they stop at generation and often yield outputs that drift in tone, topic, or style. We present PerFine, a unified, training-free critique-refine framework that enhances personalization through iterative, profile-grounded feedback. In each iteration, an LLM generator produces a draft conditioned on the retrieved profile, and a critic LLM - also conditioned on the same profile - provides structured feedback on tone, vocabulary, sentence structure, and topicality. The generator then revises, while a novel knockout strategy retains the stronger draft across iterations. We further study additional inference-time strategies such as Best-of-N and Topic Extraction to balance quality and efficiency. Across Yelp, Goodreads, and Amazon datasets, PerFine consistently improves personalization over PGraphRAG, with G-Eval gains of +8.5-12%, steady improvements over 3-5 refinement iterations, and scalability with increasing critic size. These results highlight that post-hoc, profile-aware feedback offers a powerful paradigm for personalized LLM generation that is both training-free and model-agnostic.

Related

• CARD: Cluster-level Adaptation with Reward-guided Decoding for Personalized Text Generation
• Learning to Adapt Cross-Domain Preferences via Meta-LoRA for LLM Personalization
• ExPerT: Personalizing LLM Responses to Users' Domain Expertise via Query-Wise Semantic and Keystroke Behavioral Cues

Source: arXiv cs.AI | 2026-10-15