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 2402.06216cs.IR
收藏

理解交叉熵损失在公平评估基于大语言模型的推荐系统中的作用

Understanding the Role of Cross-Entropy Loss in Fairly Evaluating Large Language Model-based Recommendation

Cong Xu, Zhangchi Zhu, Jun Wang, Jianyong Wang, Wei Zhang

AI总结:

本文从理论和实验两方面论证交叉熵损失在基于大语言模型的推荐评估中被高估,指出传统方法因损失函数替换而被低估,并呼吁建立更客观的评估体系。

摘要:

大语言模型(LLMs)在推荐系统领域已获得广泛关注;一些研究观察到,使用完整 softmax 的交叉熵损失进行微调的 LLMs 已经能够取得最先进的性能。然而,这些结论来自不客观且不公平的比较。考虑到现实中物品数量庞大,传统推荐系统通常改用逐点或逐对损失函数进行训练。但这种替代会导致严重的性能下降,从而低估了传统方法的能力,并高估了 LLMs 的排序能力。在本工作中,我们从理论上论证了交叉熵损失的优越性,并展示了在做出某些必要修改后,它可以被一些基本的近似方法充分替代。在三个公开数据集上的显著结果证实,即使从实际角度来看,现有的基于 LLM 的方法在下一项推荐任务中并不像所声称的那样有效。我们希望这些理论认识与实证结果相结合,能够促进未来对基于 LLM 的推荐系统进行客观评估。

英文摘要:

Large language models (LLMs) have gained much attention in the recommendation community; some studies have observed that LLMs, fine-tuned by the cross-entropy loss with a full softmax, could achieve state-of-the-art performance already. However, these claims are drawn from unobjective and unfair comparisons. In view of the substantial quantity of items in reality, conventional recommenders typically adopt a pointwise/pairwise loss function instead for training. This substitute however causes severe performance degradation, leading to under-estimation of conventional methods and over-confidence in the ranking capability of LLMs. In this work, we theoretically justify the superiority of cross-entropy, and showcase that it can be adequately replaced by some elementary approximations with certain necessary modifications. The remarkable results across three public datasets corroborate that even in a practical sense, existing LLM-based methods are not as effective as claimed for next-item recommendation. We hope that these theoretical understandings in conjunction with the empirical results will facilitate an objective evaluation of LLM-based recommendation in the future.

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。

↑