arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.17465cs.CLcs.AI
收藏

利用大语言模型的迭代反馈增强工具检索

Enhancing Tool Retrieval with Iterative Feedback from Large Language Models

The Hong Kong Polytechnic University(香港理工大学)

Qiancheng Xu, Yongqi Li, Heming Xia, Wenjie Li

AI总结:

本文提出利用大语言模型的多轮迭代反馈来增强工具检索,以缓解复杂指令与工具描述理解困难以及检索与使用模型不一致的问题,并通过统一基准验证了其在域内和域外评估中的先进性能。

摘要:

工具学习旨在利用外部工具增强和扩展大语言模型(LLMs)的能力,近年来受到广泛关注。现有方法表明,LLMs 可以通过上下文学习或微调有效处理一定数量的工具。然而,在现实场景中,工具数量通常非常庞大且更新不规律,这凸显了专用工具检索组件的必要性。工具检索并非易事,主要面临以下挑战:1)复杂的用户指令和工具描述;2)工具检索与工具使用模型之间的不一致。为解决上述问题,我们提出利用大语言模型的迭代反馈来增强工具检索。具体而言,我们提示工具使用模型(即 LLM)在多轮交互中为工具检索器模型提供反馈,从而逐步提升工具检索器对指令和工具的理解,并缩小两个独立组件之间的差距。我们构建了一个统一且全面的基准来评估工具检索模型。大量实验表明,我们提出的方法在域内评估和域外评估中均取得了先进的性能。

英文摘要:

Tool learning aims to enhance and expand large language models' (LLMs) capabilities with external tools, which has gained significant attention recently. Current methods have shown that LLMs can effectively handle a certain amount of tools through in-context learning or fine-tuning. However, in real-world scenarios, the number of tools is typically extensive and irregularly updated, emphasizing the necessity for a dedicated tool retrieval component. Tool retrieval is nontrivial due to the following challenges: 1) complex user instructions and tool descriptions; 2) misalignment between tool retrieval and tool usage models. To address the above issues, we propose to enhance tool retrieval with iterative feedback from the large language model. Specifically, we prompt the tool usage model, i.e., the LLM, to provide feedback for the tool retriever model in multi-round, which could progressively improve the tool retriever's understanding of instructions and tools and reduce the gap between the two standalone components. We build a unified and comprehensive benchmark to evaluate tool retrieval models. The extensive experiments indicate that our proposed approach achieves advanced performance in both in-domain evaluation and out-of-domain evaluation.

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。

↑