Tools in the Loop: Quantifying Uncertainty of LLM Question Answering Systems That Use Tools

TL;DR

This paper introduces a framework for quantifying uncertainty in LLM question answering systems that incorporate external tools, improving trustworthiness in high-stakes applications by jointly modeling uncertainties of both components.

Contribution

It presents a novel method to jointly quantify the uncertainty of LLMs and external tools, extending existing uncertainty methods to tool-calling scenarios with practical approximations.

Findings

Effective uncertainty quantification in tool-calling LLMs.

Improved trust in LLM systems for critical applications.

Validated on synthetic QA datasets and retrieval-augmented systems.

Abstract

Modern Large Language Models (LLMs) often require external tools, such as machine learning classifiers or knowledge retrieval systems, to provide accurate answers in domains where their pre-trained knowledge is insufficient. This integration of LLMs with external tools expands their utility but also introduces a critical challenge: determining the trustworthiness of responses generated by the combined system. In high-stakes applications, such as medical decision-making, it is essential to assess the uncertainty of both the LLM's generated text and the tool's output to ensure the reliability of the final response. However, existing uncertainty quantification methods do not account for the tool-calling scenario, where both the LLM and external tool contribute to the overall system's uncertainty. In this work, we present a novel framework for modeling tool-calling LLMs that quantifies uncertainty by jointly considering the predictive uncertainty of the LLM and the external tool. We extend previous methods for uncertainty quantification over token sequences to this setting and propose efficient approximations that make uncertainty computation practical for real-world applications. We evaluate our framework on two new synthetic QA datasets, derived from well-known machine learning datasets, which require tool-calling for accurate answers. Additionally, we apply our method to retrieval-augmented generation (RAG) systems and conduct a proof-of-concept experiment demonstrating the effectiveness of our uncertainty metrics in scenarios where external information retrieval is needed. Our results show that the framework is effective in enhancing trust in LLM-based systems, especially in cases where the LLM's internal knowledge is insufficient and external tools are required.