<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mehri-etal-2026-goal">
    <titleInfo>
        <title>Goal Alignment in LLM-Based User Simulators for Conversational AI</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Shuhaib</namePart>
        <namePart type="family">Mehri</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiaocheng</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Takyoung</namePart>
        <namePart type="family">Kim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Gokhan</namePart>
        <namePart type="family">Tur</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shikib</namePart>
        <namePart type="family">Mehri</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dilek</namePart>
        <namePart type="family">Hakkani-Tür</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Transactions of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>User simulators are essential to conversational AI, enabling scalable agent development and evaluation through simulated interactions. While current Large Language Models (LLMs) have advanced user simulation capabilities, we reveal that they struggle to consistently demonstrate goal-oriented behavior across multi-turn conversations, which is a critical limitation that compromises their reliability in downstream applications. We introduce User Goal State Tracking (UGST), a novel framework that tracks user goal progression throughout conversations. Leveraging UGST, we present a three-stage methodology for developing user simulators that can autonomously track goal progression and reason to generate goal-aligned responses. Moreover, we establish comprehensive evaluation metrics for measuring goal alignment in user simulators, and demonstrate that our approach yields substantial improvements across two benchmarks (MultiWOZ 2.4 and \ensuremathτ-Bench). Our contributions address a critical gap in conversational AI and establish UGST as an essential framework for developing goal-aligned user simulators. All code and data is released to facilitate future research 1.</abstract>
    <identifier type="citekey">mehri-etal-2026-goal</identifier>
    <identifier type="doi">10.1162/tacl.a.687</identifier>
    <location>
        <url>https://aclanthology.org/2026.tacl-1.38/</url>
    </location>
    <part>
        <date>2026</date>
        <detail type="volume"><number>14</number></detail>
        <extent unit="page">
            <start>852</start>
            <end>876</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Goal Alignment in LLM-Based User Simulators for Conversational AI
%A Mehri, Shuhaib
%A Yang, Xiaocheng
%A Kim, Takyoung
%A Tur, Gokhan
%A Mehri, Shikib
%A Hakkani-Tür, Dilek
%J Transactions of the Association for Computational Linguistics
%D 2026
%V 14
%I MIT Press
%C Cambridge, MA
%F mehri-etal-2026-goal
%X User simulators are essential to conversational AI, enabling scalable agent development and evaluation through simulated interactions. While current Large Language Models (LLMs) have advanced user simulation capabilities, we reveal that they struggle to consistently demonstrate goal-oriented behavior across multi-turn conversations, which is a critical limitation that compromises their reliability in downstream applications. We introduce User Goal State Tracking (UGST), a novel framework that tracks user goal progression throughout conversations. Leveraging UGST, we present a three-stage methodology for developing user simulators that can autonomously track goal progression and reason to generate goal-aligned responses. Moreover, we establish comprehensive evaluation metrics for measuring goal alignment in user simulators, and demonstrate that our approach yields substantial improvements across two benchmarks (MultiWOZ 2.4 and \ensuremathτ-Bench). Our contributions address a critical gap in conversational AI and establish UGST as an essential framework for developing goal-aligned user simulators. All code and data is released to facilitate future research 1.
%R 10.1162/tacl.a.687
%U https://aclanthology.org/2026.tacl-1.38/
%U https://doi.org/10.1162/tacl.a.687
%P 852-876

Markdown (Informal)

[Goal Alignment in LLM-Based User Simulators for Conversational AI](https://aclanthology.org/2026.tacl-1.38/) (Mehri et al., TACL 2026)

• Goal Alignment in LLM-Based User Simulators for Conversational AI (Mehri et al., TACL 2026)

ACL

• Shuhaib Mehri, Xiaocheng Yang, Takyoung Kim, Gokhan Tur, Shikib Mehri, and Dilek Hakkani-Tür. 2026. Goal Alignment in LLM-Based User Simulators for Conversational AI. Transactions of the Association for Computational Linguistics, 14:852–876.