EMNLP 2024finding0 citations

Toolken+: Improving LLM Tool Usage with Reranking and a Reject Option

Konstantin Yakovlev, Sergey Nikolenko, Andrey Bout

Abstract

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.

BibTeX
@inproceedings{yakovlev-etal-2024-toolken,
    title = "Toolken+: Improving {LLM} Tool Usage with Reranking and a Reject Option",
    author = "Yakovlev, Konstantin  and
      Nikolenko, Sergey  and
      Bout, Andrey",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.findings-emnlp.345/",
    doi = "10.18653/v1/2024.findings-emnlp.345",
    pages = "5967--5974"
}