A Survey of Uncertainty Estimation in LLMs: Theory Meets Practice
It addresses the need for systematic classification of uncertainty estimation methods in LLMs, which is critical for improving model reliability in applications like out-of-distribution detection, but it is incremental as it reviews and organizes existing literature.
This survey tackles the problem of uncertainty estimation in large language models (LLMs) by clarifying definitions and integrating theoretical perspectives to categorize methods, aiming to enhance application credibility and inspire more reliable approaches.
As large language models (LLMs) continue to evolve, understanding and quantifying the uncertainty in their predictions is critical for enhancing application credibility. However, the existing literature relevant to LLM uncertainty estimation often relies on heuristic approaches, lacking systematic classification of the methods. In this survey, we clarify the definitions of uncertainty and confidence, highlighting their distinctions and implications for model predictions. On this basis, we integrate theoretical perspectives, including Bayesian inference, information theory, and ensemble strategies, to categorize various classes of uncertainty estimation methods derived from heuristic approaches. Additionally, we address challenges that arise when applying these methods to LLMs. We also explore techniques for incorporating uncertainty into diverse applications, including out-of-distribution detection, data annotation, and question clarification. Our review provides insights into uncertainty estimation from both definitional and theoretical angles, contributing to a comprehensive understanding of this critical aspect in LLMs. We aim to inspire the development of more reliable and effective uncertainty estimation approaches for LLMs in real-world scenarios.