@inproceedings{girard-etal-2026-friendbench,
title = "{F}riend{B}ench: Benchmarking Dyadic Familiarity Inference in Humans and Multimodal Large Language Models",
author = "Girard, Jeffrey M. and
Zheng, Jason and
Vertino, Jacqueline Romero and
D{'}Avirro, Antony and
Peloquin, Benjamin",
editor = "Ghaleb, Esam and
Takmaz, Ece and
Frassinelli, Diego and
Khaertdinov, Bulat and
Fern{\'a}ndez, Raquel and
Yumak, Zerrin and
Ozyurek, Asli",
booktitle = "Proceedings of the 1st Workshop on Multimodal Interaction in Face-to-Face Dialogue",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.mint-1.14/",
pages = "127--143",
ISBN = "979-8-89176-482-8",
abstract = "Reading a social situation often depends on behavior, not words alone. We introduce FriendBench, a benchmark for inferring whether two people are already familiar or are meeting as strangers, from a 20-second clip of a dyadic ice-breaker conversation. Every pair answers the same type of prompt, so only the manner of interaction can reveal the answer. Across text, audio, and video, we compare 26 models from seven companies against matched human panels over 96 balanced dyads. The best model and the human crowd are statistically indistinguishable on accuracy in every modality, but reach it differently: humans stay balanced across the two answers, while the strongest models favor ``stranger.'' This is a difference in effective prior, not in discrimination. Richer channels help both unequally, and only humans gain from visible behavior on top of speech. We release the stimuli, human ratings, and model predictions."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="girard-etal-2026-friendbench">
<titleInfo>
<title>FriendBench: Benchmarking Dyadic Familiarity Inference in Humans and Multimodal Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jeffrey</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Girard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jason</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jacqueline</namePart>
<namePart type="given">Romero</namePart>
<namePart type="family">Vertino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antony</namePart>
<namePart type="family">D’Avirro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Peloquin</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>Proceedings of the 1st Workshop on Multimodal Interaction in Face-to-Face Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Esam</namePart>
<namePart type="family">Ghaleb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ece</namePart>
<namePart type="family">Takmaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diego</namePart>
<namePart type="family">Frassinelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bulat</namePart>
<namePart type="family">Khaertdinov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raquel</namePart>
<namePart type="family">Fernández</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zerrin</namePart>
<namePart type="family">Yumak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asli</namePart>
<namePart type="family">Ozyurek</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">979-8-89176-482-8</identifier>
</relatedItem>
<abstract>Reading a social situation often depends on behavior, not words alone. We introduce FriendBench, a benchmark for inferring whether two people are already familiar or are meeting as strangers, from a 20-second clip of a dyadic ice-breaker conversation. Every pair answers the same type of prompt, so only the manner of interaction can reveal the answer. Across text, audio, and video, we compare 26 models from seven companies against matched human panels over 96 balanced dyads. The best model and the human crowd are statistically indistinguishable on accuracy in every modality, but reach it differently: humans stay balanced across the two answers, while the strongest models favor “stranger.” This is a difference in effective prior, not in discrimination. Richer channels help both unequally, and only humans gain from visible behavior on top of speech. We release the stimuli, human ratings, and model predictions.</abstract>
<identifier type="citekey">girard-etal-2026-friendbench</identifier>
<location>
<url>https://aclanthology.org/2026.mint-1.14/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>127</start>
<end>143</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FriendBench: Benchmarking Dyadic Familiarity Inference in Humans and Multimodal Large Language Models
%A Girard, Jeffrey M.
%A Zheng, Jason
%A Vertino, Jacqueline Romero
%A D’Avirro, Antony
%A Peloquin, Benjamin
%Y Ghaleb, Esam
%Y Takmaz, Ece
%Y Frassinelli, Diego
%Y Khaertdinov, Bulat
%Y Fernández, Raquel
%Y Yumak, Zerrin
%Y Ozyurek, Asli
%S Proceedings of the 1st Workshop on Multimodal Interaction in Face-to-Face Dialogue
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-482-8
%F girard-etal-2026-friendbench
%X Reading a social situation often depends on behavior, not words alone. We introduce FriendBench, a benchmark for inferring whether two people are already familiar or are meeting as strangers, from a 20-second clip of a dyadic ice-breaker conversation. Every pair answers the same type of prompt, so only the manner of interaction can reveal the answer. Across text, audio, and video, we compare 26 models from seven companies against matched human panels over 96 balanced dyads. The best model and the human crowd are statistically indistinguishable on accuracy in every modality, but reach it differently: humans stay balanced across the two answers, while the strongest models favor “stranger.” This is a difference in effective prior, not in discrimination. Richer channels help both unequally, and only humans gain from visible behavior on top of speech. We release the stimuli, human ratings, and model predictions.
%U https://aclanthology.org/2026.mint-1.14/
%P 127-143
Markdown (Informal)
[FriendBench: Benchmarking Dyadic Familiarity Inference in Humans and Multimodal Large Language Models](https://aclanthology.org/2026.mint-1.14/) (Girard et al., MINT 2026)
ACL