Saved in:
Bibliographic Details
Main Authors: Ma, Huan, Chen, Jingdong, Zhou, Joey Tianyi, Wang, Guangyu, Zhang, Changqing
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.00290
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913827824599040
author Ma, Huan
Chen, Jingdong
Zhou, Joey Tianyi
Wang, Guangyu
Zhang, Changqing
author_facet Ma, Huan
Chen, Jingdong
Zhou, Joey Tianyi
Wang, Guangyu
Zhang, Changqing
contents Over the past few years, Large Language Models (LLMs) have developed rapidly and are widely applied in various domains. However, LLMs face the issue of hallucinations, generating responses that may be unreliable when the models lack relevant knowledge. To be aware of potential hallucinations, uncertainty estimation methods have been introduced, and most of them have confirmed that reliability lies in critical tokens. However, probability-based methods perform poorly in identifying token reliability, limiting their practical utility. In this paper, we reveal that the probability-based method fails to estimate token reliability due to the loss of evidence strength information which is accumulated in the training stage. Therefore, we present Logits-induced token uncertainty (LogTokU), a framework for estimating decoupled token uncertainty in LLMs, enabling real-time uncertainty estimation without requiring multiple sampling processes. We employ evidence modeling to implement LogTokU and use the estimated uncertainty to guide downstream tasks. The experimental results demonstrate that LogTokU has significant effectiveness and promise.
format Preprint
id arxiv_https___arxiv_org_abs_2502_00290
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Estimating LLM Uncertainty with Evidence
Ma, Huan
Chen, Jingdong
Zhou, Joey Tianyi
Wang, Guangyu
Zhang, Changqing
Computation and Language
Artificial Intelligence
Over the past few years, Large Language Models (LLMs) have developed rapidly and are widely applied in various domains. However, LLMs face the issue of hallucinations, generating responses that may be unreliable when the models lack relevant knowledge. To be aware of potential hallucinations, uncertainty estimation methods have been introduced, and most of them have confirmed that reliability lies in critical tokens. However, probability-based methods perform poorly in identifying token reliability, limiting their practical utility. In this paper, we reveal that the probability-based method fails to estimate token reliability due to the loss of evidence strength information which is accumulated in the training stage. Therefore, we present Logits-induced token uncertainty (LogTokU), a framework for estimating decoupled token uncertainty in LLMs, enabling real-time uncertainty estimation without requiring multiple sampling processes. We employ evidence modeling to implement LogTokU and use the estimated uncertainty to guide downstream tasks. The experimental results demonstrate that LogTokU has significant effectiveness and promise.
title Estimating LLM Uncertainty with Evidence
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2502.00290