MARS: Meaning-Aware Response Scoring for Uncertainty Estimation in Generative LLMs

TL;DR

This paper introduces MARS, a novel meaning-aware scoring method for uncertainty estimation in generative LLMs, improving reliability by considering semantic contributions of tokens, validated across multiple datasets and models.

Contribution

Proposes MARS, a semantic-aware scoring function that enhances uncertainty estimation in generative LLMs over traditional length-normalized methods.

Findings

MARS significantly improves uncertainty estimation performance.

MARS outperforms length-normalized scoring across multiple datasets.

Validated effectiveness on medical question-answering data.

Abstract

Generative Large Language Models (LLMs) are widely utilized for their excellence in various tasks. However, their tendency to produce inaccurate or misleading outputs poses a potential risk, particularly in high-stakes environments. Therefore, estimating the correctness of generative LLM outputs is an important task for enhanced reliability. Uncertainty Estimation (UE) in generative LLMs is an evolving domain, where SOTA probability-based methods commonly employ length-normalized scoring. In this work, we propose Meaning-Aware Response Scoring (MARS) as an alternative to length-normalized scoring for UE methods. MARS is a novel scoring function that considers the semantic contribution of each token in the generated sequence in the context of the question. We demonstrate that integrating MARS into UE methods results in a universal and significant improvement in UE performance. We conduct experiments using three distinct closed-book question-answering datasets across five popular pre-trained LLMs. Lastly, we validate the efficacy of MARS on a Medical QA dataset. Code can be found https://github.com/Ybakman/LLM_Uncertainity.