面向基于大型语言模型推荐的强化提示个性化
Reinforced Prompt Personalization for Recommendation with Large Language Models
AI总结：
针对任务级提示忽略用户差异的问题，提出强化提示个性化方法RPP及RPP+，通过多智能体在句子级别为用户个性化离散提示并动态优化动作，显著提升了LLMs的推荐性能。
摘要：
设计有效的提示可以赋能 LLMs 理解用户偏好，并提供具备意图理解和知识利用能力的推荐。然而，近期的研究主要集中在任务级提示上，开发了在给定推荐任务（如评分或排序）中所有用户共享的固定提示模板。尽管很方便，但任务级提示忽略了个体的用户差异，导致对用户兴趣的分析不准确。在这项工作中，我们引入了实例级提示的概念，旨在为单个用户个性化离散提示。为此，我们提出了 Reinforced Prompt Personalization (RPP) 来自动实现这一点。为了提高效率和质量，RPP 在句子级别个性化提示，而不是在庞大的词汇表中逐词搜索。具体来说，RPP 将提示分解为四种模式，基于多智能体定制模式并将它们组合。然后，个性化的提示与 LLMs（环境）迭代交互，以提升 LLMs 的推荐性能（奖励）。除了 RPP，为了提高动作空间的可扩展性，我们提出的 RPP+ 在整个迭代过程中利用 LLMs 动态优化所选动作。在多个数据集上的大量实验证明了 RPP/RPP+ 相较于传统推荐模型、少样本方法和其他基于提示的方法的优越性，强调了实例级提示在用于推荐的 LLMs 中的重要性。我们的代码可在 https://github.com/maowenyu-11/RPP 获取。
英文摘要：
Designing effective prompts can empower LLMs to understand user preferences and provide recommendations with intent comprehension and knowledge utilization capabilities. Nevertheless, recent studies predominantly concentrate on task-wise prompting, developing fixed prompt templates shared across all users in a given recommendation task (e.g., rating or ranking). Although convenient, task-wise prompting overlooks individual user differences, leading to inaccurate analysis of user interests. In this work, we introduce the concept of instance-wise prompting, aiming at personalizing discrete prompts for individual users. Toward this end, we propose Reinforced Prompt Personalization (RPP) to realize it automatically. To improve efficiency and quality, RPP personalizes prompts at the sentence level rather than searching in the vast vocabulary word-by-word. Specifically, RPP breaks down the prompt into four patterns, tailoring patterns based on multi-agent and combining them. Then the personalized prompts interact with LLMs (environment) iteratively, to boost LLMs' recommending performance (reward). In addition to RPP, to improve the scalability of action space, our proposal of RPP+ dynamically refines the selected actions with LLMs throughout the iterative process. Extensive experiments on various datasets demonstrate the superiority of RPP/RPP+ over traditional recommender models, few-shot methods, and other prompt-based methods, underscoring the significance of instance-wise prompting in LLMs for recommendation. Our code is available at https://github.com/maowenyu-11/RPP.
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。
