Shapley Uncertainty in Natural Language Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhu, Meilin, Jin, Gaojie, Huang, Xiaowei, Zhang, Lijun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911081552674816
author Zhu, Meilin
Jin, Gaojie
Huang, Xiaowei
Zhang, Lijun
author_facet Zhu, Meilin
Jin, Gaojie
Huang, Xiaowei
Zhang, Lijun
contents In question-answering tasks, determining when to trust the outputs is crucial to the alignment of large language models (LLMs). Kuhn et al. (2023) introduces semantic entropy as a measure of uncertainty, by incorporating linguistic invariances from the same meaning. It primarily relies on setting threshold to measure the level of semantic equivalence relation. We propose a more nuanced framework that extends beyond such thresholding by developing a Shapley-based uncertainty metric that captures the continuous nature of semantic relationships. We establish three fundamental properties that characterize valid uncertainty metrics and prove that our Shapley uncertainty satisfies these criteria. Through extensive experiments, we demonstrate that our Shapley uncertainty more accurately predicts LLM performance in question-answering and other datasets, compared to similar baseline measures.
format Preprint
id arxiv_https___arxiv_org_abs_2507_21406
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Shapley Uncertainty in Natural Language Generation
Zhu, Meilin
Jin, Gaojie
Huang, Xiaowei
Zhang, Lijun
Artificial Intelligence
In question-answering tasks, determining when to trust the outputs is crucial to the alignment of large language models (LLMs). Kuhn et al. (2023) introduces semantic entropy as a measure of uncertainty, by incorporating linguistic invariances from the same meaning. It primarily relies on setting threshold to measure the level of semantic equivalence relation. We propose a more nuanced framework that extends beyond such thresholding by developing a Shapley-based uncertainty metric that captures the continuous nature of semantic relationships. We establish three fundamental properties that characterize valid uncertainty metrics and prove that our Shapley uncertainty satisfies these criteria. Through extensive experiments, we demonstrate that our Shapley uncertainty more accurately predicts LLM performance in question-answering and other datasets, compared to similar baseline measures.
title Shapley Uncertainty in Natural Language Generation
topic Artificial Intelligence
url https://arxiv.org/abs/2507.21406