A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions

TL;DR

This survey reviews uncertainty quantification methods for large language models, categorizing existing approaches, discussing their applications, and highlighting open challenges to improve trustworthiness and reliability.

Contribution

It provides a comprehensive taxonomy of uncertainty quantification techniques for LLMs and discusses their applications and open research challenges.

Findings

Existing methods are categorized within a unified taxonomy.

Uncertainty quantification can help detect hallucinations in LLM outputs.

Open challenges include developing more accurate and scalable uncertainty measures.

Abstract

The remarkable performance of large language models (LLMs) in content generation, coding, and common-sense reasoning has spurred widespread integration into many facets of society. However, integration of LLMs raises valid questions on their reliability and trustworthiness, given their propensity to generate hallucinations: plausible, factually-incorrect responses, which are expressed with striking confidence. Previous work has shown that hallucinations and other non-factual responses generated by LLMs can be detected by examining the uncertainty of the LLM in its response to the pertinent prompt, driving significant research efforts devoted to quantifying the uncertainty of LLMs. This survey seeks to provide an extensive review of existing uncertainty quantification methods for LLMs, identifying their salient features, along with their strengths and weaknesses. We present existing methods within a relevant taxonomy, unifying ostensibly disparate methods to aid understanding of the state of the art. Furthermore, we highlight applications of uncertainty quantification methods for LLMs, spanning chatbot and textual applications to embodied artificial intelligence applications in robotics. We conclude with open research challenges in uncertainty quantification of LLMs, seeking to motivate future research.