@inproceedings{yan-2026-growtheval,
title = "{GROWTHEVAL}: Evaluating Stage-Conditioned Developmental Realism in Role-Playing {LLM}s",
author = "Yan, Danping",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.aacl-long.136/",
pages = "2974--2996",
ISBN = "979-8-89176-439-2",
abstract = "Large language models (LLMs) are increasingly used as role-playing dialogue agents in long-horizon applications such as tutoring, companionship, and narrative interaction, where users may expect stable persona consistency as well as plausible stage-conditioned change. Existing evaluations emphasize static persona fidelity, temporal factuality, or isolated social skills, but rarely test whether role-playing models produce coherent developmental differentiation across ordered stages. We introduce GROWTHEVAL, a psychology-inspired diagnostic framework for assessing stage-conditioned developmental realism in single-turn, stage-isolated role-playing responses. Using stage-conditioned scenarios and multi-axis scoring, \textsc{GrowthEval} evaluates cross-stage patterns in developmental appropriateness, role-play coherence, and canon fidelity across five socio-emotional dimensions. Across the evaluated LLMs, we observe a model-tiered empirical pattern: higher-capacity models respond more consistently to stage conditioning but can over-mature at early stages, whereas lower-capacity models exhibit flatter and weakly differentiated profiles. Reliability and robustness analyses provide evidence for the stability of these findings. Overall, the evaluated LLMs only partially realize coherent, stage-appropriate developmental change. GROWTHEVAL provides an extensible diagnostic framework for analyzing stage-conditioned behavioral differentiation and associated failure modes in single-turn role-playing responses."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yan-2026-growtheval">
<titleInfo>
<title>GROWTHEVAL: Evaluating Stage-Conditioned Developmental Realism in Role-Playing LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Danping</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-439-2</identifier>
</relatedItem>
<abstract>Large language models (LLMs) are increasingly used as role-playing dialogue agents in long-horizon applications such as tutoring, companionship, and narrative interaction, where users may expect stable persona consistency as well as plausible stage-conditioned change. Existing evaluations emphasize static persona fidelity, temporal factuality, or isolated social skills, but rarely test whether role-playing models produce coherent developmental differentiation across ordered stages. We introduce GROWTHEVAL, a psychology-inspired diagnostic framework for assessing stage-conditioned developmental realism in single-turn, stage-isolated role-playing responses. Using stage-conditioned scenarios and multi-axis scoring, GrowthEval evaluates cross-stage patterns in developmental appropriateness, role-play coherence, and canon fidelity across five socio-emotional dimensions. Across the evaluated LLMs, we observe a model-tiered empirical pattern: higher-capacity models respond more consistently to stage conditioning but can over-mature at early stages, whereas lower-capacity models exhibit flatter and weakly differentiated profiles. Reliability and robustness analyses provide evidence for the stability of these findings. Overall, the evaluated LLMs only partially realize coherent, stage-appropriate developmental change. GROWTHEVAL provides an extensible diagnostic framework for analyzing stage-conditioned behavioral differentiation and associated failure modes in single-turn role-playing responses.</abstract>
<identifier type="citekey">yan-2026-growtheval</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-long.136/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>2974</start>
<end>2996</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GROWTHEVAL: Evaluating Stage-Conditioned Developmental Realism in Role-Playing LLMs
%A Yan, Danping
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-439-2
%F yan-2026-growtheval
%X Large language models (LLMs) are increasingly used as role-playing dialogue agents in long-horizon applications such as tutoring, companionship, and narrative interaction, where users may expect stable persona consistency as well as plausible stage-conditioned change. Existing evaluations emphasize static persona fidelity, temporal factuality, or isolated social skills, but rarely test whether role-playing models produce coherent developmental differentiation across ordered stages. We introduce GROWTHEVAL, a psychology-inspired diagnostic framework for assessing stage-conditioned developmental realism in single-turn, stage-isolated role-playing responses. Using stage-conditioned scenarios and multi-axis scoring, GrowthEval evaluates cross-stage patterns in developmental appropriateness, role-play coherence, and canon fidelity across five socio-emotional dimensions. Across the evaluated LLMs, we observe a model-tiered empirical pattern: higher-capacity models respond more consistently to stage conditioning but can over-mature at early stages, whereas lower-capacity models exhibit flatter and weakly differentiated profiles. Reliability and robustness analyses provide evidence for the stability of these findings. Overall, the evaluated LLMs only partially realize coherent, stage-appropriate developmental change. GROWTHEVAL provides an extensible diagnostic framework for analyzing stage-conditioned behavioral differentiation and associated failure modes in single-turn role-playing responses.
%U https://aclanthology.org/2026.aacl-long.136/
%P 2974-2996
Markdown (Informal)
[GROWTHEVAL: Evaluating Stage-Conditioned Developmental Realism in Role-Playing LLMs](https://aclanthology.org/2026.aacl-long.136/) (Yan, AACL-IJCNLP 2026)
ACL