@inproceedings{yu-etal-2026-remp,
title = "{REMP}: A Structured Event-Probing Benchmark for Long-Horizon Role-Playing Dialogue",
author = "Yu, Qianxi and
Dan, Yuhao and
Bai, Qingchun and
Chen, Qin and
Zhou, Jie and
He, Liang",
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.602/",
pages = "12702--12722",
ISBN = "979-8-89176-462-0",
abstract = "Large language models (LLMs) are increasingly used in role-playing applications, yet evaluating whether they maintain character-consistent behavior over extended interactions remains challenging. Existing benchmarks mostly focus on short exchanges, static long-context inputs, or isolated aspects of role-playing, making long-horizon failures difficult to diagnose. We present REMP (Relationship-Emotion-Memory-Persona), a structured event-probing benchmark for long-horizon role-playing dialogue. REMP constructs multi-chapter dialogue trajectories from character profiles and embeds diagnostic probe events targeting persona consistency, emotional consistency, memory integrity, and relational continuity. We further introduce REMP-EVAL, an anchor-based multi-turn evaluation protocol that assesses model behavior after event triggers using dimension-specific references. The current release contains 160 characters organized into 80 dialogue trajectories, each averaging about 60 sessions and 800 turns. Experiments on 11 LLMs show that memory integrity and emotional consistency are the main bottlenecks, indicating that long-horizon role-playing requires not only long-context retrieval but also sustained affective and relational consistency."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yu-etal-2026-remp">
<titleInfo>
<title>REMP: A Structured Event-Probing Benchmark for Long-Horizon Role-Playing Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qianxi</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuhao</namePart>
<namePart type="family">Dan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qingchun</namePart>
<namePart type="family">Bai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qin</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liang</namePart>
<namePart type="family">He</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>Large language models (LLMs) are increasingly used in role-playing applications, yet evaluating whether they maintain character-consistent behavior over extended interactions remains challenging. Existing benchmarks mostly focus on short exchanges, static long-context inputs, or isolated aspects of role-playing, making long-horizon failures difficult to diagnose. We present REMP (Relationship-Emotion-Memory-Persona), a structured event-probing benchmark for long-horizon role-playing dialogue. REMP constructs multi-chapter dialogue trajectories from character profiles and embeds diagnostic probe events targeting persona consistency, emotional consistency, memory integrity, and relational continuity. We further introduce REMP-EVAL, an anchor-based multi-turn evaluation protocol that assesses model behavior after event triggers using dimension-specific references. The current release contains 160 characters organized into 80 dialogue trajectories, each averaging about 60 sessions and 800 turns. Experiments on 11 LLMs show that memory integrity and emotional consistency are the main bottlenecks, indicating that long-horizon role-playing requires not only long-context retrieval but also sustained affective and relational consistency.</abstract>
<identifier type="citekey">yu-etal-2026-remp</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.602/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>12702</start>
<end>12722</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T REMP: A Structured Event-Probing Benchmark for Long-Horizon Role-Playing Dialogue
%A Yu, Qianxi
%A Dan, Yuhao
%A Bai, Qingchun
%A Chen, Qin
%A Zhou, Jie
%A He, Liang
%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 yu-etal-2026-remp
%X Large language models (LLMs) are increasingly used in role-playing applications, yet evaluating whether they maintain character-consistent behavior over extended interactions remains challenging. Existing benchmarks mostly focus on short exchanges, static long-context inputs, or isolated aspects of role-playing, making long-horizon failures difficult to diagnose. We present REMP (Relationship-Emotion-Memory-Persona), a structured event-probing benchmark for long-horizon role-playing dialogue. REMP constructs multi-chapter dialogue trajectories from character profiles and embeds diagnostic probe events targeting persona consistency, emotional consistency, memory integrity, and relational continuity. We further introduce REMP-EVAL, an anchor-based multi-turn evaluation protocol that assesses model behavior after event triggers using dimension-specific references. The current release contains 160 characters organized into 80 dialogue trajectories, each averaging about 60 sessions and 800 turns. Experiments on 11 LLMs show that memory integrity and emotional consistency are the main bottlenecks, indicating that long-horizon role-playing requires not only long-context retrieval but also sustained affective and relational consistency.
%U https://aclanthology.org/2026.findings-emnlp.602/
%P 12702-12722
Markdown (Informal)
[REMP: A Structured Event-Probing Benchmark for Long-Horizon Role-Playing Dialogue](https://aclanthology.org/2026.findings-emnlp.602/) (Yu et al., Findings 2026)
ACL