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.- Anthology ID:
- 2024.findings-emnlp.345
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2024
- Month:
- November
- Year:
- 2024
- Address:
- Miami, Florida, USA
- Editors:
- Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 5967–5974
- Language:
- URL:
- https://preview.aclanthology.org/icon-24-ingestion/2024.findings-emnlp.345/
- DOI:
- 10.18653/v1/2024.findings-emnlp.345
- Cite (ACL):
- Konstantin Yakovlev, Sergey Nikolenko, and Andrey Bout. 2024. Toolken+: Improving LLM Tool Usage with Reranking and a Reject Option. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 5967–5974, Miami, Florida, USA. Association for Computational Linguistics.
- Cite (Informal):
- Toolken+: Improving LLM Tool Usage with Reranking and a Reject Option (Yakovlev et al., Findings 2024)
- PDF:
- https://preview.aclanthology.org/icon-24-ingestion/2024.findings-emnlp.345.pdf