Logo image
Back
SConU: Selective Conformal Uncertainty in Large Language Models
Conference proceeding   Open access

SConU: Selective Conformal Uncertainty in Large Language Models

Zhiyuan Wang, Qingni Wang, Yue Zhang, Tianlong Chen, Xiaofeng Zhu, Xiaoshuang Shi and Kaidi Xu
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics, v 1, pp 19052-19075
2025
DOI: https://doi.org/10.18653/v1/2025.acl-long.934
url
https://doi.org/10.18653/v1/2025.acl-long.934View
Published, Version of Record (VoR) Open CC BY V4.0

Abstract

Artificial Intelligence or Cybernetics
As large language models are increasingly utilized in real-world applications, guarantees of task-specific metrics are essential for their reliable deployment. Previous studies have introduced various criteria of conformal uncertainty grounded in split conformal prediction, which offer user-specified correctness coverage. However, existing frameworks often fail to identify uncertainty data outliers that violate the exchangeability assumption, leading to unbounded miscoverage rates and unactionable prediction sets. In this paper, we propose a novel approach termed Selective Conformal Uncertainty (SConU), which, for the first time, implements significance tests, by developing two conformal p-values that are instrumental in determining whether a given sample deviates from the uncertainty distribution of the calibration set at a specific manageable risk level. Our approach not only facilitates rigorous management of miscoverage rates across both single-domain and interdisciplinary contexts, but also enhances the efficiency of predictions. Furthermore, we comprehensively analyze the components of the conformal procedures, aiming to approximate conditional coverage, particularly in high-stakes question-answering tasks.

Metrics

12 Record Views

Details

Logo image