Can Large Language Models Faithfully Express Their Intrinsic Uncertainty in Words?

TL;DR

This paper investigates whether large language models can accurately express their inherent uncertainty in natural language, revealing that current models often fail to communicate their confidence levels effectively, which impacts trustworthiness.

Contribution

The paper introduces a formal metric for assessing the faithfulness of LLMs in expressing their uncertainty and evaluates multiple models, highlighting the need for better alignment.

Findings

Modern LLMs poorly convey their uncertainty

The proposed metric effectively measures uncertainty expression

Better alignment improves trustworthiness of LLMs

Abstract

We posit that large language models (LLMs) should be capable of expressing their intrinsic uncertainty in natural language. For example, if the LLM is equally likely to output two contradicting answers to the same question, then its generated response should reflect this uncertainty by hedging its answer (e.g., "I'm not sure, but I think..."). We formalize faithful response uncertainty based on the gap between the model's intrinsic confidence in the assertions it makes and the decisiveness by which they are conveyed. This example-level metric reliably indicates whether the model reflects its uncertainty, as it penalizes both excessive and insufficient hedging. We evaluate a variety of aligned LLMs at faithfully communicating uncertainty on several knowledge-intensive question answering tasks. Our results provide strong evidence that modern LLMs are poor at faithfully conveying their uncertainty, and that better alignment is necessary to improve their trustworthiness.