@inproceedings{zhang-etal-2026-uncertainty,
title = "Uncertainty-o: One Model-agnostic Framework for Unveiling Uncertainty in Large Multimodal Models",
author = "Zhang, Ruiyang and
Zhang, Junhao and
Fei, Hao and
Zheng, Zhedong",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.110/",
pages = "2270--2285",
ISBN = "979-8-89176-462-0",
abstract = "Large Multimodal Models (LMMs), characterized by their humanoid perception and generation capabilities, have been widely applied in critical physical world scenarios, yet their uncertainty remains mostly unknown. In this paper, we aim to answer three substantial questions: (1) Can we explicitly capture the uncertainty of LMMs? (2) How can we tackle the reasoning complexity arising from prompts across various modalities? (3) How can we quantify the uncertainty of LMMs when their responses extend to multiple modalities, beyond mere text? To answer these questions, we propose Uncertainty-o: (1) Uncertainty-o can explicitly estimate uncertainty of LMMs, with prompts and responses across five modalities, namely text, image, audio, video, and point cloud. (2) We propose multimodal prompt perturbation, where empirical studies indicate that semantically equivalent perturbations are more effective for eliciting LMM uncertainty. (3) We introduce multimodal semantic uncertainty, enabling uncertainty estimation when LMMs generate multimodal responses. Extensive quantitative and qualitative analyses validate the efficacy of Uncertainty-o in reliably estimating the uncertainty inherent in LMMs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-uncertainty">
<titleInfo>
<title>Uncertainty-o: One Model-agnostic Framework for Unveiling Uncertainty in Large Multimodal Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruiyang</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junhao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Fei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhedong</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Large Multimodal Models (LMMs), characterized by their humanoid perception and generation capabilities, have been widely applied in critical physical world scenarios, yet their uncertainty remains mostly unknown. In this paper, we aim to answer three substantial questions: (1) Can we explicitly capture the uncertainty of LMMs? (2) How can we tackle the reasoning complexity arising from prompts across various modalities? (3) How can we quantify the uncertainty of LMMs when their responses extend to multiple modalities, beyond mere text? To answer these questions, we propose Uncertainty-o: (1) Uncertainty-o can explicitly estimate uncertainty of LMMs, with prompts and responses across five modalities, namely text, image, audio, video, and point cloud. (2) We propose multimodal prompt perturbation, where empirical studies indicate that semantically equivalent perturbations are more effective for eliciting LMM uncertainty. (3) We introduce multimodal semantic uncertainty, enabling uncertainty estimation when LMMs generate multimodal responses. Extensive quantitative and qualitative analyses validate the efficacy of Uncertainty-o in reliably estimating the uncertainty inherent in LMMs.</abstract>
<identifier type="citekey">zhang-etal-2026-uncertainty</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.110/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>2270</start>
<end>2285</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Uncertainty-o: One Model-agnostic Framework for Unveiling Uncertainty in Large Multimodal Models
%A Zhang, Ruiyang
%A Zhang, Junhao
%A Fei, Hao
%A Zheng, Zhedong
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F zhang-etal-2026-uncertainty
%X Large Multimodal Models (LMMs), characterized by their humanoid perception and generation capabilities, have been widely applied in critical physical world scenarios, yet their uncertainty remains mostly unknown. In this paper, we aim to answer three substantial questions: (1) Can we explicitly capture the uncertainty of LMMs? (2) How can we tackle the reasoning complexity arising from prompts across various modalities? (3) How can we quantify the uncertainty of LMMs when their responses extend to multiple modalities, beyond mere text? To answer these questions, we propose Uncertainty-o: (1) Uncertainty-o can explicitly estimate uncertainty of LMMs, with prompts and responses across five modalities, namely text, image, audio, video, and point cloud. (2) We propose multimodal prompt perturbation, where empirical studies indicate that semantically equivalent perturbations are more effective for eliciting LMM uncertainty. (3) We introduce multimodal semantic uncertainty, enabling uncertainty estimation when LMMs generate multimodal responses. Extensive quantitative and qualitative analyses validate the efficacy of Uncertainty-o in reliably estimating the uncertainty inherent in LMMs.
%U https://aclanthology.org/2026.findings-emnlp.110/
%P 2270-2285
Markdown (Informal)
[Uncertainty-o: One Model-agnostic Framework for Unveiling Uncertainty in Large Multimodal Models](https://aclanthology.org/2026.findings-emnlp.110/) (Zhang et al., Findings 2026)
ACL