Iterative Critique-Refine Framework for Enhancing LLM Personalization

TL;DR

PerFine introduces an iterative critique-refine framework that enhances personalized text generation by using profile-grounded feedback, improving tone, style, and topicality without additional training.

Contribution

It presents a training-free, critique-refine approach with a novel knockout strategy and inference-time enhancements for better personalization in LLMs.

Findings

Consistently improves personalization metrics over existing methods.

Achieves +7-13% gains in GEval scores across datasets.

Scales effectively with larger critic models and multiple refinement iterations.

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 GEval gains of +7-13%, 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.