用于增强大语言模型个性化的迭代批评-精炼框架
Iterative Critique-Refine Framework for Enhancing LLM Personalization
AI总结：
针对现有检索增强个性化文本生成方法易出现风格语气偏移的问题，提出无需训练的PerFine迭代批评-精炼框架，通过结构化反馈与淘汰策略优化生成，在多数据集上显著提升个性化效果。
摘要：
个性化文本生成要求模型不仅能生成连贯文本，还要与目标用户的风格、语气及主题关注点对齐。现有的检索增强方法，如LaMP（语言模型个性化基准）和PGraphRAG（图检索增强生成个性化方法），虽利用用户及邻域历史丰富用户画像，但仅止步于生成阶段，输出常出现语气、主题或风格偏移。我们提出PerFine，这是一个统一的、无需训练的批评-精炼框架，通过基于用户画像的迭代反馈增强个性化效果。每轮迭代中，大语言模型生成器根据检索到的用户画像生成草稿，同样基于该画像的批评器大语言模型会从语气、词汇、句式结构和主题相关性四个方面提供结构化反馈，生成器随后进行修改，同时一种新颖的淘汰策略会在各轮迭代中保留质量更优的草稿。我们进一步研究了推理阶段的额外策略，如Best-of-N（N选最佳）和主题提取，以平衡生成质量与效率。在Yelp、Goodreads和Amazon三个数据集上，PerFine的个性化效果始终优于PGraphRAG，GEval（生成评估指标）得分提升7-13%，在3-5轮精炼迭代中持续提升，且可随批评器模型规模增大实现可扩展性提升。这些结果表明，基于画像感知的事后反馈为大语言模型个性化生成提供了一种既无需训练又不依赖特定模型的强大范式。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
