用推理链优化推荐，让大模型更懂用户真实意图。
Reasoning to Rank: An End-to-End Solution for Exploiting Large Language Models for Recommendation
- 在用户-物品层面逐步推理，避免位置偏差
- 结合强化学习端到端训练，直接优化推荐效果
- 在多个数据集上优于传统与主流LLM推荐方法
推荐系统需推断用户不断变化的偏好并按意图排序物品，这要求超越模式匹配的深层推理。近期研究开始利用大语言模型（LLMs）进行推荐，但如何有效优化模型以提升推荐实用性仍待探索。本文提出「Reasoning to Rank」，一个将推荐实用性优化内化至LLM分步推理学习中的端到端训练框架。为避免LLM推理中的位置偏差并实现推理过程的直接优化，该框架在用户-物品层级进行推理，并采用强化学习进行端到端训练。在三个Amazon数据集和一个大规模工业数据集上的实验表明，其性能持续优于强基线的常规与基于LLM的推荐方案。深入分析验证了框架关键组件的必要性，并为该方向的未来发展提供了启示。
原文摘要 · Abstract (English)
Recommender systems are tasked to infer users' evolving preferences and rank items aligned with their intents, which calls for in-depth reasoning beyond pattern-based scoring. Recent efforts start to leverage large language models (LLMs) for recommendation, but how to effectively optimize the model for improved recommendation utility is still under explored. In this work, we propose Reasoning to Rank, an end-to-end training framework that internalizes recommendation utility optimization into the learning of step-by-step reasoning in LLMs. To avoid position bias in LLM reasoning and enable direct optimization of the reasoning process, our framework performs reasoning at the user-item level and employs reinforcement learning for end-to-end training of the LLM. Experiments on three Amazon datasets and a large-scale industrial dataset showed consistent gains over strong conventional and LLM-based solutions. Extensive in-depth analyses validate the necessity of the key components in the proposed framework and shed lights on the future developments of this line of work.
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。