提升大模型工具调用准确率，通过重排序与拒答选项减少误用。
Toolken+: Improving LLM Tool Usage with Reranking and a Reject Option
- 对工具候选集进行重排序，利用文档信息优化选择。
- 引入拒答选项，当不确定时直接拒绝调用工具。
- 在多步数学推理任务中显著降低错误率，适合复杂工具调用场景。
最近提出的 ToolkenGPT 工具学习范式表现良好，但存在两大问题：无法利用工具文档，且常错误判断是否应使用工具。本文提出 Toolken+，通过重排序 ToolkenGPT 选出的前 k 个工具来缓解第一个问题，并引入特殊“拒答”选项，使模型在“拒答”被排第一时生成对应词汇标记。实验表明，Toolken+ 在多步数值推理和工具选择任务中均有效提升性能。
原文摘要 · Abstract (English)
The recently proposed ToolkenGPT tool learning paradigm demonstrates promising performance but suffers from two major issues: first, it cannot benefit from tool documentation, and second, it often makes mistakes in whether to use a tool at all. We introduce Toolken+ that mitigates the first problem by reranking top $k$ tools selected by ToolkenGPT and the second problem with a special "Reject" option such that the model will generate a vocabulary token if "Reject" is ranked first. We demonstrate the effectiveness of Toolken+ on multistep numerical reasoning and tool selection tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。