自动优化推荐重排序的提示词，提升个性化效果
Automating Personalization: Prompt Optimization for Recommendation Reranking
- 通过位置感知反馈机制精准修正排名
- 批量训练结合聚合反馈，提升模型泛化能力
- 适合需要自动化个性化推荐的系统开发者
现代推荐系统越来越多地利用大语言模型（LLMs）进行重排序以提升个性化。然而，现有方法存在两大局限：(1) 过度依赖人工设计的提示词，难以扩展；(2) 对非结构化物品元数据处理不足，影响偏好推断。我们提出AGP（Auto-Guided Prompt Refinement）框架，可自动优化用户画像生成提示词以实现个性化重排序。AGP引入两项关键创新：(1) 位置感知反馈机制，实现精准排名修正；(2) 批量训练与聚合反馈，增强模型泛化能力。
原文摘要 · Abstract (English)
Modern recommender systems increasingly leverage large language models (LLMs) for reranking to improve personalization. However, existing approaches face two key limitations: (1) heavy reliance on manually crafted prompts that are difficult to scale, and (2) inadequate handling of unstructured item metadata that complicates preference inference. We present AGP (Auto-Guided Prompt Refinement), a novel framework that automatically optimizes user profile generation prompts for personalized reranking. AGP introduces two key innovations: (1) position-aware feedback mechanisms for precise ranking correction, and (2) batched training with aggregated feedback to enhance generalization.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。