@inproceedings{sun-etal-2025-posum,
title = "{P}o{S}um-Bench: Benchmarking Position Bias in {LLM}-based Conversational Summarization",
author = "Sun, Xu and
Delphin-Poulat, Lionel and
Tarnec, Christ{\`e}le and
Shimorina, Anastasia",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.404/",
pages = "7996--8020",
ISBN = "979-8-89176-332-6",
abstract = "Large language models (LLMs) are increasingly used for zero-shot conversation summarization, but often exhibit positional bias{---}tending to overemphasize content from the beginning or end of a conversation while neglecting the middle. To address this issue, we introduce PoSum-Bench, a comprehensive benchmark for evaluating positional bias in conversational summarization, featuring diverse English and French conversational datasets spanning formal meetings, casual conversations, and customer service interactions. We propose a novel semantic similarity-based sentence-level metric to quantify the direction and magnitude of positional bias in model-generated summaries, enabling systematic and reference-free evaluation across conversation positions, languages, and conversational contexts.Our benchmark and methodology thus provide the first systematic, cross-lingual framework for reference-free evaluation of positional bias in conversational summarization, laying the groundwork for developing more balanced and unbiased summarization models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sun-etal-2025-posum">
<titleInfo>
<title>PoSum-Bench: Benchmarking Position Bias in LLM-based Conversational Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xu</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lionel</namePart>
<namePart type="family">Delphin-Poulat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christèle</namePart>
<namePart type="family">Tarnec</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anastasia</namePart>
<namePart type="family">Shimorina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>Large language models (LLMs) are increasingly used for zero-shot conversation summarization, but often exhibit positional bias—tending to overemphasize content from the beginning or end of a conversation while neglecting the middle. To address this issue, we introduce PoSum-Bench, a comprehensive benchmark for evaluating positional bias in conversational summarization, featuring diverse English and French conversational datasets spanning formal meetings, casual conversations, and customer service interactions. We propose a novel semantic similarity-based sentence-level metric to quantify the direction and magnitude of positional bias in model-generated summaries, enabling systematic and reference-free evaluation across conversation positions, languages, and conversational contexts.Our benchmark and methodology thus provide the first systematic, cross-lingual framework for reference-free evaluation of positional bias in conversational summarization, laying the groundwork for developing more balanced and unbiased summarization models.</abstract>
<identifier type="citekey">sun-etal-2025-posum</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.404/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>7996</start>
<end>8020</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PoSum-Bench: Benchmarking Position Bias in LLM-based Conversational Summarization
%A Sun, Xu
%A Delphin-Poulat, Lionel
%A Tarnec, Christèle
%A Shimorina, Anastasia
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F sun-etal-2025-posum
%X Large language models (LLMs) are increasingly used for zero-shot conversation summarization, but often exhibit positional bias—tending to overemphasize content from the beginning or end of a conversation while neglecting the middle. To address this issue, we introduce PoSum-Bench, a comprehensive benchmark for evaluating positional bias in conversational summarization, featuring diverse English and French conversational datasets spanning formal meetings, casual conversations, and customer service interactions. We propose a novel semantic similarity-based sentence-level metric to quantify the direction and magnitude of positional bias in model-generated summaries, enabling systematic and reference-free evaluation across conversation positions, languages, and conversational contexts.Our benchmark and methodology thus provide the first systematic, cross-lingual framework for reference-free evaluation of positional bias in conversational summarization, laying the groundwork for developing more balanced and unbiased summarization models.
%U https://aclanthology.org/2025.emnlp-main.404/
%P 7996-8020
Markdown (Informal)
[PoSum-Bench: Benchmarking Position Bias in LLM-based Conversational Summarization](https://aclanthology.org/2025.emnlp-main.404/) (Sun et al., EMNLP 2025)
ACL