Built independently by an author, for readers. Read the story and support ChapterPal
ChapterPal Logo
Log inSign up

keyword

factual confidence

Factual confidence is a measure of the degree of certainty or probability that a language model or computational system assigns to the truthfulness and factual accuracy of its generated statements or knowledge claims. Distinct from general predictive certainty over next tokens in a sequence, it specifically assesses whether the information conveyed reflects established, real-world facts rather than hallucinations or erroneous assertions. Techniques for estimating factual confidence typically include evaluating output likelihoods, probing internal neural representations, and measuring the stability of model responses across semantically equivalent queries. Accurately quantifying factual confidence is essential for determining the trustworthiness and reliability of artificial intelligence outputs in knowledge-intensive tasks such as fact-checking, question answering, and automated reasoning.

1 item

Factual Confidence of LLMs: on Reliability and Robustness of Current Estimators

Factual Confidence of LLMs: on Reliability and Robustness of Current Estimators

Matéo Mahaut, Laura Aina, Paula Czarnowska, Momchil Hardalov, Thomas Müller, Lluís Màrquez

OrganizationsAmazon Web ServicesUniversitat Pompeu Fabra

Why you should read this

Evaluates five major families of factual confidence estimators across multiple large language models and tasks, revealing that internal hidden-state probes achieve superior reliability while exposing how easily model confidence fluctuates across semantically equivalent prompts.

Large Language Models (LLMs) tend to be unreliable in the factuality of their answers. To address this problem, NLP researchers have proposed a range of techniques to estimate LLM’s confidence over facts. However, due to the lack of a systematic comparison, it is not clear how the different methods compare to one another. To fill this gap, we present a survey and empirical comparison of estimators of factual confidence. We define an experimental framework allowing for fair comparison, covering both fact-verification and question answering. Our experiments across a series of LLMs indicate that trained hidden-state probes provide the most reliable confidence estimates, albeit at the expense of requiring access to weights and training data. We also conduct a deeper assessment of factual confidence by measuring the consistency of model behavior under meaning-preserving variations in the input. We find that the confidence of LLMs is often unstable across semantically equivalent inputs, suggesting that there is much room for improvement of the stability of models’ parametric knowledge. Our code is available at https://github.com/amazon-science/factual-confidence-of-llms.

Added

2026-10-03