Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraph

2025-03-19

Roman Vashurin *

Ekaterina Fadeeva

Artem Vazhentsev

Lyudmila Rvanova

Daniil Vasilev

Akim Tsvigun

Sergey Petrakov

Rui Xing

Abdelrahman Sadallah

Kirill Grishchenkov

Alexander Panchenko

Timothy Baldwin

Preslav Nakov

Maxim Panov

Artem Shelmanov

DOI：10.1162/tacl_a_00737

Original

Original request for help

Save

Abstract

En 中文

The rapid proliferation of large language models (LLMs) has stimulated researchers to seek effective and efficient approaches to deal with LLM hallucinations and low-quality outputs. Uncertainty quantification (UQ) is a key element of machine learning applications in dealing with such challenges. However, research to date on UQ for LLMs has been fragmented in terms of techniques and evaluation methodologies. In this work, we address this issue by introducing a novel benchmark that implements a collection of state-of-the-art UQ baselines and offers an environment for controllable and consistent evaluation of novel UQ techniques over various text generation tasks. Our benchmark also supports the assessment of confidence normalization methods in terms of their ability to provide interpretable scores. Using our benchmark, we conduct a large-scale empirical investigation of UQ and normalization techniques across eleven tasks, identifying the most effective approaches.

Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraph

Abstract

Journal

Organization

Cited Papers

Citing Papers