@inproceedings{chen-etal-2026-meetingqa2,
title = "{MEETINGQA}2: A Generative Speaker-Centric Benchmark for Multi-Party Dialogue Question Answering",
author = "Chen, Yuhan and
Li, Yanling and
Zou, Bowei and
Fan, Yifan and
Hong, Yu",
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.1728/",
doi = "10.18653/2026.findings-emnlp.1728",
pages = "36957--36967",
ISBN = "979-8-89176-462-0",
abstract = "Multi-party Dialogue Question Answering (MDQA) requires the machine to answer questions based on a conversation with multiple interlocutors. Existing benchmarks are largely extractive, leaving positional shortcuts and providing limited evidence about whether models can synthesize distributed evidence into speaker-grounded answers. We introduce MEETINGQA2, the first generative MDQA benchmark, derived from MEETINGQA with reformulated questions and speaker-centric summary answers. It contains 1,033 QA pairs, including 108 unanswerable questions. Beyond standard overlap metrics, we introduce attribution accuracy and factual correctness. Experiments show that strong LLMs perform consistently worse on MEETINGQA2 than on MEETINGQA, with especially large drops in attribution accuracy. The results indicate persistent weaknesses in speaker attribution, factual grounding, and long-context dialogue understanding."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2026-meetingqa2">
<titleInfo>
<title>MEETINGQA2: A Generative Speaker-Centric Benchmark for Multi-Party Dialogue Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuhan</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanling</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bowei</namePart>
<namePart type="family">Zou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yifan</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Hong</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>Multi-party Dialogue Question Answering (MDQA) requires the machine to answer questions based on a conversation with multiple interlocutors. Existing benchmarks are largely extractive, leaving positional shortcuts and providing limited evidence about whether models can synthesize distributed evidence into speaker-grounded answers. We introduce MEETINGQA2, the first generative MDQA benchmark, derived from MEETINGQA with reformulated questions and speaker-centric summary answers. It contains 1,033 QA pairs, including 108 unanswerable questions. Beyond standard overlap metrics, we introduce attribution accuracy and factual correctness. Experiments show that strong LLMs perform consistently worse on MEETINGQA2 than on MEETINGQA, with especially large drops in attribution accuracy. The results indicate persistent weaknesses in speaker attribution, factual grounding, and long-context dialogue understanding.</abstract>
<identifier type="citekey">chen-etal-2026-meetingqa2</identifier>
<identifier type="doi">10.18653/2026.findings-emnlp.1728</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1728/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>36957</start>
<end>36967</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MEETINGQA2: A Generative Speaker-Centric Benchmark for Multi-Party Dialogue Question Answering
%A Chen, Yuhan
%A Li, Yanling
%A Zou, Bowei
%A Fan, Yifan
%A Hong, Yu
%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 chen-etal-2026-meetingqa2
%X Multi-party Dialogue Question Answering (MDQA) requires the machine to answer questions based on a conversation with multiple interlocutors. Existing benchmarks are largely extractive, leaving positional shortcuts and providing limited evidence about whether models can synthesize distributed evidence into speaker-grounded answers. We introduce MEETINGQA2, the first generative MDQA benchmark, derived from MEETINGQA with reformulated questions and speaker-centric summary answers. It contains 1,033 QA pairs, including 108 unanswerable questions. Beyond standard overlap metrics, we introduce attribution accuracy and factual correctness. Experiments show that strong LLMs perform consistently worse on MEETINGQA2 than on MEETINGQA, with especially large drops in attribution accuracy. The results indicate persistent weaknesses in speaker attribution, factual grounding, and long-context dialogue understanding.
%R 10.18653/2026.findings-emnlp.1728
%U https://aclanthology.org/2026.findings-emnlp.1728/
%U https://doi.org/10.18653/2026.findings-emnlp.1728
%P 36957-36967
Markdown (Informal)
[MEETINGQA2: A Generative Speaker-Centric Benchmark for Multi-Party Dialogue Question Answering](https://aclanthology.org/2026.findings-emnlp.1728/) (Chen et al., Findings 2026)
ACL