<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2026-prefinfer">
    <titleInfo>
        <title>PREFINFER: Preference Inference from User-LLM Interaction History</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yufei</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hao</namePart>
        <namePart type="family">Peng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yunjia</namePart>
        <namePart type="family">Qi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lei</namePart>
        <namePart type="family">Hou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bin</namePart>
        <namePart type="family">Xu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Juanzi</namePart>
        <namePart type="family">Li</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 model (LLM) personalization aims to generate responses that align with individual user preferences, making accurate preference inference critical. In practice, user-LLM interaction histories naturally contain rich preference signals. However, extracting preferences from these histories remains underexplored and challenging: the history can be long and noisy, preferences may evolve over time, and preferences may vary across situations even within the same topic. To address these challenges, we develop PREFINFER, a model that accurately infers user preferences from the user’s interaction history with an LLM. Specifically, we introduce PREFMINE, an automated data construction method that synthesizes high-quality preference inference data, where each sample includes a synthetic interaction history, a current user request, and the user’s preference for the current request, and construct PREFMINE-15K for training PREFINFER. Experiments show that PREFINFER achieves advanced performance on preference inference, and the preferences inferred by PREFINFER effectively guide LLMs to generate responses better aligned with user preferences. We conduct thorough ablation studies on the key design choices of PREFMINE, validating their effectiveness. We have released the code, data, and models to facilitate further research(https://github.com/THU-KEG/PREFINFER).</abstract>
    <identifier type="citekey">chen-etal-2026-prefinfer</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.700/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>14690</start>
            <end>14712</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T PREFINFER: Preference Inference from User-LLM Interaction History
%A Chen, Yufei
%A Peng, Hao
%A Qi, Yunjia
%A Hou, Lei
%A Xu, Bin
%A Li, Juanzi
%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-prefinfer
%X Large language model (LLM) personalization aims to generate responses that align with individual user preferences, making accurate preference inference critical. In practice, user-LLM interaction histories naturally contain rich preference signals. However, extracting preferences from these histories remains underexplored and challenging: the history can be long and noisy, preferences may evolve over time, and preferences may vary across situations even within the same topic. To address these challenges, we develop PREFINFER, a model that accurately infers user preferences from the user’s interaction history with an LLM. Specifically, we introduce PREFMINE, an automated data construction method that synthesizes high-quality preference inference data, where each sample includes a synthetic interaction history, a current user request, and the user’s preference for the current request, and construct PREFMINE-15K for training PREFINFER. Experiments show that PREFINFER achieves advanced performance on preference inference, and the preferences inferred by PREFINFER effectively guide LLMs to generate responses better aligned with user preferences. We conduct thorough ablation studies on the key design choices of PREFMINE, validating their effectiveness. We have released the code, data, and models to facilitate further research(https://github.com/THU-KEG/PREFINFER).
%U https://aclanthology.org/2026.findings-emnlp.700/
%P 14690-14712

Markdown (Informal)

[PREFINFER: Preference Inference from User-LLM Interaction History](https://aclanthology.org/2026.findings-emnlp.700/) (Chen et al., Findings 2026)

• PREFINFER: Preference Inference from User-LLM Interaction History (Chen et al., Findings 2026)

ACL

• Yufei Chen, Hao Peng, Yunjia Qi, Lei Hou, Bin Xu, and Juanzi Li. 2026. PREFINFER: Preference Inference from User-LLM Interaction History. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 14690–14712, Budapest, Hungary. Association for Computational Linguistics.