Probabilities Are All You Need: A Probability-Only Approach to Uncertainty Estimation in Large Language Models
This addresses uncertainty estimation for LLMs to reduce hallucinations, but it is incremental as it builds on existing probability-based methods with an adaptive mechanism.
The paper tackles the problem of hallucinations in large language models by proposing an efficient, training-free uncertainty estimation method that uses top-K probabilities to approximate predictive entropy, outperforming state-of-the-art baselines on three question-answering datasets.
Large Language Models (LLMs) exhibit strong performance across various natural language processing (NLP) tasks but remain vulnerable to hallucinations, generating factually incorrect or misleading outputs. Uncertainty estimation, often using predictive entropy estimation, is key to addressing this issue. However, existing methods often require multiple samples or extra computation to assess semantic entropy. This paper proposes an efficient, training-free uncertainty estimation method that approximates predictive entropy using the responses' top-$K$ probabilities. Moreover, we employ an adaptive mechanism to determine $K$ to enhance flexibility and filter out low-confidence probabilities. Experimental results on three free-form question-answering datasets across several LLMs demonstrate that our method outperforms expensive state-of-the-art baselines, contributing to the broader goal of enhancing LLM trustworthiness.