@inproceedings{gomes-etal-2026-beitscore,
title = "{BE}i{TS}core++: Reference-free Image Captioning Evaluation with {BE}i{T}-3 and Conformalized Quantile Regression",
author = "Gomes, Goncalo Emanuel Cavaco and
Martins, Bruno and
Zerva, Chrysoula",
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.2160/",
pages = "46192--46226",
ISBN = "979-8-89176-462-0",
abstract = "Reliable uncertainty estimation is important for deploying evaluation metrics in real-world settings, where both input ambiguity and domain shifts are common. In this work, we propose an uncertainty-aware extension of the BEiTScore image captioning metric, producing calibrated confidence intervals alongside alignment scores. Our approach models predictive distributions over human judgments, enabling both accurate scoring and principled uncertainty quantification. We evaluate our BEiTScore++ metric across multiple benchmarks with human-annotated ratings, demonstrating strong performance in terms of ranking correlation, calibration, and interval sharpness. BEiTScore++ not only produces accurate predictions, but also captures aleatoric uncertainty arising from ambiguous inputs, and epistemic uncertainty due to limited model knowledge, making it a reliable tool for uncertainty-aware evaluation of image-caption alignment."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gomes-etal-2026-beitscore">
<titleInfo>
<title>BEiTScore++: Reference-free Image Captioning Evaluation with BEiT-3 and Conformalized Quantile Regression</title>
</titleInfo>
<name type="personal">
<namePart type="given">Goncalo</namePart>
<namePart type="given">Emanuel</namePart>
<namePart type="given">Cavaco</namePart>
<namePart type="family">Gomes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bruno</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chrysoula</namePart>
<namePart type="family">Zerva</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>Reliable uncertainty estimation is important for deploying evaluation metrics in real-world settings, where both input ambiguity and domain shifts are common. In this work, we propose an uncertainty-aware extension of the BEiTScore image captioning metric, producing calibrated confidence intervals alongside alignment scores. Our approach models predictive distributions over human judgments, enabling both accurate scoring and principled uncertainty quantification. We evaluate our BEiTScore++ metric across multiple benchmarks with human-annotated ratings, demonstrating strong performance in terms of ranking correlation, calibration, and interval sharpness. BEiTScore++ not only produces accurate predictions, but also captures aleatoric uncertainty arising from ambiguous inputs, and epistemic uncertainty due to limited model knowledge, making it a reliable tool for uncertainty-aware evaluation of image-caption alignment.</abstract>
<identifier type="citekey">gomes-etal-2026-beitscore</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.2160/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>46192</start>
<end>46226</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BEiTScore++: Reference-free Image Captioning Evaluation with BEiT-3 and Conformalized Quantile Regression
%A Gomes, Goncalo Emanuel Cavaco
%A Martins, Bruno
%A Zerva, Chrysoula
%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 gomes-etal-2026-beitscore
%X Reliable uncertainty estimation is important for deploying evaluation metrics in real-world settings, where both input ambiguity and domain shifts are common. In this work, we propose an uncertainty-aware extension of the BEiTScore image captioning metric, producing calibrated confidence intervals alongside alignment scores. Our approach models predictive distributions over human judgments, enabling both accurate scoring and principled uncertainty quantification. We evaluate our BEiTScore++ metric across multiple benchmarks with human-annotated ratings, demonstrating strong performance in terms of ranking correlation, calibration, and interval sharpness. BEiTScore++ not only produces accurate predictions, but also captures aleatoric uncertainty arising from ambiguous inputs, and epistemic uncertainty due to limited model knowledge, making it a reliable tool for uncertainty-aware evaluation of image-caption alignment.
%U https://aclanthology.org/2026.findings-emnlp.2160/
%P 46192-46226
Markdown (Informal)
[BEiTScore++: Reference-free Image Captioning Evaluation with BEiT-3 and Conformalized Quantile Regression](https://aclanthology.org/2026.findings-emnlp.2160/) (Gomes et al., Findings 2026)
ACL