arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2411.00331cs.IR
收藏

超越效用:评估LLM作为推荐器

Beyond Utility: Evaluating LLM as Recommender

Tsinghua University(清华大学);University of Waterloo(滑铁卢大学);Huawei Noah’s Ark Lab(华为诺亚方舟实验室)

Chumeng Jiang, Jiayin Wang, Weizhi Ma, Charles L. A. Clarke, Shuai Wang, Chuhan Wu, Min Zhang

AI总结:

本文提出多维评估框架,从历史长度敏感性、候选位置偏差、生成性能和幻觉四个新维度评估LLM推荐器,发现其在排序和重排序任务中优于传统模型,但存在位置偏差和幻觉问题。

摘要:

随着大型语言模型(LLMs)的快速发展,近期研究将LLMs用作推荐器,为不同用户提供个性化信息服务。尽管努力提高基于LLM的推荐模型的准确性,但对超越效用维度的关注相对较少。此外,基于LLM的推荐模型具有独特的评估方面,这些方面在很大程度上被忽视了。为弥补这一差距,我们探索了四个新的评估维度,并提出了一个多维评估框架。新的评估维度包括:1)历史长度敏感性,2)候选位置偏差,3)涉及生成的性能,以及4)幻觉。所有四个维度都可能影响性能,但在传统系统中大多无需考虑。使用此多维评估框架以及传统方面,我们评估了七个基于LLM的推荐器在三种提示策略下的性能,并将其与六个传统模型在四个数据集上的排序和重排序任务进行了比较。我们发现,LLMs在处理具有先验知识和较短输入历史的排序任务时表现出色,并且在重排序设置中表现更好,在多个维度上超越了传统模型。然而,LLMs表现出显著的候选位置偏差问题,并且一些模型产生不存在物品的幻觉频率远高于其他模型。我们希望我们的评估框架和观察结果能有益于未来关于LLMs作为推荐器的研究。代码和数据可在以下网址获取:此https URL。

英文摘要:

With the rapid development of Large Language Models (LLMs), recent studies employed LLMs as recommenders to provide personalized information services for distinct users. Despite efforts to improve the accuracy of LLM-based recommendation models, relatively little attention is paid to beyond-utility dimensions. Moreover, there are unique evaluation aspects of LLM-based recommendation models, which have been largely ignored. To bridge this gap, we explore four new evaluation dimensions and propose a multidimensional evaluation framework. The new evaluation dimensions include: 1) history length sensitivity, 2) candidate position bias, 3) generation-involved performance, and 4) hallucinations. All four dimensions have the potential to impact performance, but are largely unnecessary for consideration in traditional systems. Using this multidimensional evaluation framework, along with traditional aspects, we evaluate the performance of seven LLM-based recommenders, with three prompting strategies, comparing them with six traditional models on both ranking and re-ranking tasks on four datasets. We find that LLMs excel at handling tasks with prior knowledge and shorter input histories in the ranking setting, and perform better in the re-ranking setting, beating traditional models across multiple dimensions. However, LLMs exhibit substantial candidate position bias issues, and some models hallucinate nonexistent items much more often than others. We intend our evaluation framework and observations to benefit future research on the use of LLMs as recommenders. The code and data are available at https://github.com/JiangDeccc/EvaLLMasRecommender.

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。

↑