Uncertainty Calibration for Tool-Using Language Agents

Hao Liu, Zi-Yi Dou, Yixin Wang, Nanyun Peng, Yisong Yue


Abstract
There is increasing interest in equipping language models with the ability to leverage external tools for complex, goal-oriented tasks. However, interacting with external tools introduces inherent uncertainties due to imperfections and misalignments between the tools’ outputs and the agents’ internal models, often leading to suboptimal outcomes. We thus study the problem of tool-use calibration in language agents, and identify prompt design and execution trace selection as two primary areas that suffer from miscalibration. We then propose ProbeCal, which recalibrates the internal probabilities of tool-using language agents to better reflect the actual effectiveness of tool, and enables a more appropriate selection of prompts and execution paths. We empirically show that ProbeCal can significantly and consistently improve off-the-shelf language models in tool-using applications.
Anthology ID:
2024.findings-emnlp.978
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:
16781–16805
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.978
DOI:
Bibkey:
Cite (ACL):
Hao Liu, Zi-Yi Dou, Yixin Wang, Nanyun Peng, and Yisong Yue. 2024. Uncertainty Calibration for Tool-Using Language Agents. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 16781–16805, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Uncertainty Calibration for Tool-Using Language Agents (Liu et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.978.pdf