<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="iwata-etal-2026-identifying">
    <titleInfo>
        <title>Identifying User-Inference-Dependent Out-of-Character Behavior in LLM-Based Role-Playing Agents</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Shinji</namePart>
        <namePart type="family">Iwata</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shiki</namePart>
        <namePart type="family">Sato</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jun</namePart>
        <namePart type="family">Baba</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Koya</namePart>
        <namePart type="family">Ihara</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Michimasa</namePart>
        <namePart type="family">Inaba</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>For the practical deployment of the Role-Playing Agents with Large Language Models, prior work has mainly focused on suppressing out-of-character behavior relative to explicitly provided character information such as personas. However, as shown in psychological research, out-of-character behavior can arise not only from contradictions with explicit information but also from mismatches with character images implicitly inferred by users. Modeling user-inference-dependent out-of-character behavior is a challenging task, because it is unclear what kinds of inferences users make from existing information. To tackle this problem, we construct a dataset of 480 dialogue scenarios and collect 2,152 descriptions from users familiar with those titles. Using cases that annotators judged inappropriate despite the absence of contradiction with existing settings, we derive a 12-category typology, organized into general, title-specific, and individual-specific groups. We also conduct an exploratory evaluation of category-guided feedback, finding no consistent overall advantage over standard self-refinement but possible benefits for some characters. Our shareable code and dataset are at https://github.com/CyberAgentAILab/User-Inference-OOC.</abstract>
    <identifier type="citekey">iwata-etal-2026-identifying</identifier>
    <location>
        <url>https://aclanthology.org/2026.aacl-long.220/</url>
    </location>
    <part>
        <date>2026-11</date>
        <extent unit="page">
            <start>4927</start>
            <end>4943</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Identifying User-Inference-Dependent Out-of-Character Behavior in LLM-Based Role-Playing Agents
%A Iwata, Shinji
%A Sato, Shiki
%A Baba, Jun
%A Ihara, Koya
%A Inaba, Michimasa
%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 iwata-etal-2026-identifying
%X For the practical deployment of the Role-Playing Agents with Large Language Models, prior work has mainly focused on suppressing out-of-character behavior relative to explicitly provided character information such as personas. However, as shown in psychological research, out-of-character behavior can arise not only from contradictions with explicit information but also from mismatches with character images implicitly inferred by users. Modeling user-inference-dependent out-of-character behavior is a challenging task, because it is unclear what kinds of inferences users make from existing information. To tackle this problem, we construct a dataset of 480 dialogue scenarios and collect 2,152 descriptions from users familiar with those titles. Using cases that annotators judged inappropriate despite the absence of contradiction with existing settings, we derive a 12-category typology, organized into general, title-specific, and individual-specific groups. We also conduct an exploratory evaluation of category-guided feedback, finding no consistent overall advantage over standard self-refinement but possible benefits for some characters. Our shareable code and dataset are at https://github.com/CyberAgentAILab/User-Inference-OOC.
%U https://aclanthology.org/2026.aacl-long.220/
%P 4927-4943

Markdown (Informal)

[Identifying User-Inference-Dependent Out-of-Character Behavior in LLM-Based Role-Playing Agents](https://aclanthology.org/2026.aacl-long.220/) (Iwata et al., AACL-IJCNLP 2026)

• Identifying User-Inference-Dependent Out-of-Character Behavior in LLM-Based Role-Playing Agents (Iwata et al., AACL-IJCNLP 2026)

ACL

• Shinji Iwata, Shiki Sato, Jun Baba, Koya Ihara, and Michimasa Inaba. 2026. Identifying User-Inference-Dependent Out-of-Character Behavior in LLM-Based Role-Playing Agents. In 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), pages 4927–4943, Hengqin, China. Association for Computational Linguistics.