arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2411.10697cs.NE
收藏

用于推荐系统的语言模型进化算法:基准与算法比较

Language Model Evolutionary Algorithms for Recommender Systems: Benchmarks and Algorithm Comparisons

Nanyang Technological University(南洋理工大学);Singapore University of Technology and Design(新加坡科技设计大学);Centre for Frontier AI Research, A*STAR(前沿人工智能研究中心,A*STAR);Institute of High Performance Computing, A*STAR(高性能计算研究所,A*STAR)

Jiao Liu, Zhu Sun, Shanshan Feng, Caishun Chen, Yew-Soon Ong

AI总结:

本文提出面向基于LLM的推荐系统的基准集RSBench,用于评估进化算法在推荐提示优化中的表现,并通过三种基于LLM的进化算法实验验证其有效性。

摘要:

在进化计算领域,大语言模型(LLMs)卓越的语言处理能力和推理能力显著增强了进化算法(EAs)的功能,使其能够处理涉及结构化语言或程序代码的优化问题。尽管该领域仍处于早期阶段,但其巨大潜力已推动了多种基于LLM的进化算法的开发。为了有效评估这些基于LLM的进化算法的性能和实际适用性,具有现实意义的基准至关重要。本文聚焦于基于LLM的推荐系统(RSs),引入了一个名为RSBench的基准问题集,专门用于评估基于LLM的进化算法在推荐提示优化中的表现。RSBench以会话式推荐为重点,旨在发现一组帕累托最优提示,用于指导推荐过程,从而提供准确、多样且公平的推荐。我们基于成熟的进化算法框架开发了三种基于LLM的进化算法,并使用RSBench对其性能进行了实验评估。我们的研究为进化算法在基于LLM的推荐系统中的应用提供了有价值的见解。此外,我们探索了可能影响推荐系统整体性能的关键组件,为未来基于LLM的进化算法在推荐系统中的发展研究提供了有意义的指导。所提出的RSBench源代码可在https://github.com/LiuJ-2023/RSBench/tree/main获取。

英文摘要:

In the evolutionary computing community, the remarkable language-handling capabilities and reasoning power of large language models (LLMs) have significantly enhanced the functionality of evolutionary algorithms (EAs), enabling them to tackle optimization problems involving structured language or program code. Although this field is still in its early stages, its impressive potential has led to the development of various LLM-based EAs. To effectively evaluate the performance and practical applicability of these LLM-based EAs, benchmarks with real-world relevance are essential. In this paper, we focus on LLM-based recommender systems (RSs) and introduce a benchmark problem set, named RSBench, specifically designed to assess the performance of LLM-based EAs in recommendation prompt optimization. RSBench emphasizes session-based recommendations, aiming to discover a set of Pareto optimal prompts that guide the recommendation process, providing accurate, diverse, and fair recommendations. We develop three LLM-based EAs based on established EA frameworks and experimentally evaluate their performance using RSBench. Our study offers valuable insights into the application of EAs in LLM-based RSs. Additionally, we explore key components that may influence the overall performance of the RS, providing meaningful guidance for future research on the development of LLM-based EAs in RSs. The source code of the proposed RSBench can be found at https://github.com/LiuJ-2023/RSBench/tree/main.

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。

↑