@inproceedings{rezaei-etal-2025-egonormia,
title = "{E}go{N}ormia: Benchmarking Physical-Social Norm Understanding",
author = "Rezaei, MohammadHossein and
Fu, Yicheng and
Cuvin, Phil and
Ziems, Caleb and
Zhang, Yanzhe and
Zhu, Hao and
Yang, Diyi",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.985/",
doi = "10.18653/v1/2025.findings-acl.985",
pages = "19256--19283",
ISBN = "979-8-89176-256-5",
abstract = "Human activity is moderated by norms; however, supervision for normative reasoning is sparse, particularly where norms are physically- or socially-grounded. We thus present EgoNormia $\lVert \epsilon \rVert$, comprising 1,853 (200 for EgoNormia-verified) multiple choice questions (MCQs) grounded within ego-centric videos of human interactions, enabling the evaluation and improvement of normative reasoning in vision-language models (VLMs). spans seven norm categories: safety, privacy, proxemics, politeness, cooperation, coordination/proactivity, and communication/legibility. To compile this dataset at scale, we propose a novel pipeline to generate grounded MCQs from raw egocentric video. Our work demonstrates that current state-of-the-art VLMs lack robust grounded norm understanding, scoring a maximum of 54{\%} on EgoNormia and 58{\%} on EgoNormia-verified, with performance across norm categories indicating significant risks of safety and privacy when VLMs are used in real-world agents. We additionally explore methods for improving normative understanding, demonstrating a naive retrieval-based generation (RAG) method using can enhance normative reasoning in VLMs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rezaei-etal-2025-egonormia">
<titleInfo>
<title>EgoNormia: Benchmarking Physical-Social Norm Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">MohammadHossein</namePart>
<namePart type="family">Rezaei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yicheng</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phil</namePart>
<namePart type="family">Cuvin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Caleb</namePart>
<namePart type="family">Ziems</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanzhe</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">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diyi</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>Human activity is moderated by norms; however, supervision for normative reasoning is sparse, particularly where norms are physically- or socially-grounded. We thus present EgoNormia łVert ε \rVert, comprising 1,853 (200 for EgoNormia-verified) multiple choice questions (MCQs) grounded within ego-centric videos of human interactions, enabling the evaluation and improvement of normative reasoning in vision-language models (VLMs). spans seven norm categories: safety, privacy, proxemics, politeness, cooperation, coordination/proactivity, and communication/legibility. To compile this dataset at scale, we propose a novel pipeline to generate grounded MCQs from raw egocentric video. Our work demonstrates that current state-of-the-art VLMs lack robust grounded norm understanding, scoring a maximum of 54% on EgoNormia and 58% on EgoNormia-verified, with performance across norm categories indicating significant risks of safety and privacy when VLMs are used in real-world agents. We additionally explore methods for improving normative understanding, demonstrating a naive retrieval-based generation (RAG) method using can enhance normative reasoning in VLMs.</abstract>
<identifier type="citekey">rezaei-etal-2025-egonormia</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.985</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.985/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>19256</start>
<end>19283</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EgoNormia: Benchmarking Physical-Social Norm Understanding
%A Rezaei, MohammadHossein
%A Fu, Yicheng
%A Cuvin, Phil
%A Ziems, Caleb
%A Zhang, Yanzhe
%A Zhu, Hao
%A Yang, Diyi
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F rezaei-etal-2025-egonormia
%X Human activity is moderated by norms; however, supervision for normative reasoning is sparse, particularly where norms are physically- or socially-grounded. We thus present EgoNormia łVert ε \rVert, comprising 1,853 (200 for EgoNormia-verified) multiple choice questions (MCQs) grounded within ego-centric videos of human interactions, enabling the evaluation and improvement of normative reasoning in vision-language models (VLMs). spans seven norm categories: safety, privacy, proxemics, politeness, cooperation, coordination/proactivity, and communication/legibility. To compile this dataset at scale, we propose a novel pipeline to generate grounded MCQs from raw egocentric video. Our work demonstrates that current state-of-the-art VLMs lack robust grounded norm understanding, scoring a maximum of 54% on EgoNormia and 58% on EgoNormia-verified, with performance across norm categories indicating significant risks of safety and privacy when VLMs are used in real-world agents. We additionally explore methods for improving normative understanding, demonstrating a naive retrieval-based generation (RAG) method using can enhance normative reasoning in VLMs.
%R 10.18653/v1/2025.findings-acl.985
%U https://aclanthology.org/2025.findings-acl.985/
%U https://doi.org/10.18653/v1/2025.findings-acl.985
%P 19256-19283
Markdown (Informal)
[EgoNormia: Benchmarking Physical-Social Norm Understanding](https://aclanthology.org/2025.findings-acl.985/) (Rezaei et al., Findings 2025)
ACL
- MohammadHossein Rezaei, Yicheng Fu, Phil Cuvin, Caleb Ziems, Yanzhe Zhang, Hao Zhu, and Diyi Yang. 2025. EgoNormia: Benchmarking Physical-Social Norm Understanding. In Findings of the Association for Computational Linguistics: ACL 2025, pages 19256–19283, Vienna, Austria. Association for Computational Linguistics.