When2Call: When (not) to Call Tools
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916708898308096 |
|---|---|
| author | Ross, Hayley Mahabaleshwarkar, Ameya Sunil Suhara, Yoshi |
| author_facet | Ross, Hayley Mahabaleshwarkar, Ameya Sunil Suhara, Yoshi |
| contents | Leveraging external tools is a key feature for modern Language Models (LMs) to expand their capabilities and integrate them into existing systems. However, existing benchmarks primarily focus on the accuracy of tool calling -- whether the correct tool is called with the correct parameters -- and less on evaluating when LMs should (not) call tools. We develop a new benchmark, When2Call, which evaluates tool-calling decision-making: when to generate a tool call, when to ask follow-up questions and when to admit the question can't be answered with the tools provided. We find that state-of-the-art tool-calling LMs show significant room for improvement on When2Call, indicating the importance of this benchmark. We also develop a training set for When2Call and leverage the multiple-choice nature of the benchmark to develop a preference optimization training regime, which shows considerably more improvement than traditional fine-tuning. We release the benchmark and training data as well as evaluation scripts at https://github.com/NVIDIA/When2Call. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_18851 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | When2Call: When (not) to Call Tools Ross, Hayley Mahabaleshwarkar, Ameya Sunil Suhara, Yoshi Computation and Language Leveraging external tools is a key feature for modern Language Models (LMs) to expand their capabilities and integrate them into existing systems. However, existing benchmarks primarily focus on the accuracy of tool calling -- whether the correct tool is called with the correct parameters -- and less on evaluating when LMs should (not) call tools. We develop a new benchmark, When2Call, which evaluates tool-calling decision-making: when to generate a tool call, when to ask follow-up questions and when to admit the question can't be answered with the tools provided. We find that state-of-the-art tool-calling LMs show significant room for improvement on When2Call, indicating the importance of this benchmark. We also develop a training set for When2Call and leverage the multiple-choice nature of the benchmark to develop a preference optimization training regime, which shows considerably more improvement than traditional fine-tuning. We release the benchmark and training data as well as evaluation scripts at https://github.com/NVIDIA/When2Call. |
| title | When2Call: When (not) to Call Tools |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2504.18851 |