@inproceedings{qi-etal-2026-xchoice,
title = "{XC}hoice: Explainable Evaluation of {AI}{--}Human Alignment in {LLM}-based Constrained Choice Decision Making",
author = "Qi, Weihong and
Huang, Fan and
Muralidharan, Rasika and
An, Jisun and
Kwak, Haewoon",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {IJCNLP}-{AACL} 2026",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-aacl.194/",
pages = "3833--3861",
ISBN = "979-8-89176-444-6",
abstract = "We present XChoice, an explainable framework for evaluating AI-human alignment in constrained decision making. Moving beyond outcome agreement such as accuracy and F1 score, XChoice fits a mechanism-based decision model to human data and LLM-generated decisions, recovering interpretable parameters that capture the relative importance of decision factors, constraint sensitivity, and implied trade-offs. Alignment is assessed by comparing these parameter vectors across models, options, and subgroups. We demonstrate XChoice on Americans' daily time allocation using the American Time Use Survey (ATUS) as human ground truth, revealing heterogeneous alignment across models and activities and salient misalignment concentrated in subgroups defined by race (Black respondents) and marital status (Spouse: Present). We further validate robustness of XChoice via an invariance analysis and evaluate targeted mitigation with a retrieval-augmented generation (RAG) intervention. Overall, XChoice provides mechanism-based metrics that diagnose misalignment beyond surface outcome matching and make the effects of targeted interventions measurable at the mechanism level. Code and data access instructions are available at https://github.com/WeihongQ/xchoice."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qi-etal-2026-xchoice">
<titleInfo>
<title>XChoice: Explainable Evaluation of AI–Human Alignment in LLM-based Constrained Choice Decision Making</title>
</titleInfo>
<name type="personal">
<namePart type="given">Weihong</namePart>
<namePart type="family">Qi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fan</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rasika</namePart>
<namePart type="family">Muralidharan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jisun</namePart>
<namePart type="family">An</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haewoon</namePart>
<namePart type="family">Kwak</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>Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026</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">979-8-89176-444-6</identifier>
</relatedItem>
<abstract>We present XChoice, an explainable framework for evaluating AI-human alignment in constrained decision making. Moving beyond outcome agreement such as accuracy and F1 score, XChoice fits a mechanism-based decision model to human data and LLM-generated decisions, recovering interpretable parameters that capture the relative importance of decision factors, constraint sensitivity, and implied trade-offs. Alignment is assessed by comparing these parameter vectors across models, options, and subgroups. We demonstrate XChoice on Americans’ daily time allocation using the American Time Use Survey (ATUS) as human ground truth, revealing heterogeneous alignment across models and activities and salient misalignment concentrated in subgroups defined by race (Black respondents) and marital status (Spouse: Present). We further validate robustness of XChoice via an invariance analysis and evaluate targeted mitigation with a retrieval-augmented generation (RAG) intervention. Overall, XChoice provides mechanism-based metrics that diagnose misalignment beyond surface outcome matching and make the effects of targeted interventions measurable at the mechanism level. Code and data access instructions are available at https://github.com/WeihongQ/xchoice.</abstract>
<identifier type="citekey">qi-etal-2026-xchoice</identifier>
<location>
<url>https://aclanthology.org/2026.findings-aacl.194/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>3833</start>
<end>3861</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T XChoice: Explainable Evaluation of AI–Human Alignment in LLM-based Constrained Choice Decision Making
%A Qi, Weihong
%A Huang, Fan
%A Muralidharan, Rasika
%A An, Jisun
%A Kwak, Haewoon
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-444-6
%F qi-etal-2026-xchoice
%X We present XChoice, an explainable framework for evaluating AI-human alignment in constrained decision making. Moving beyond outcome agreement such as accuracy and F1 score, XChoice fits a mechanism-based decision model to human data and LLM-generated decisions, recovering interpretable parameters that capture the relative importance of decision factors, constraint sensitivity, and implied trade-offs. Alignment is assessed by comparing these parameter vectors across models, options, and subgroups. We demonstrate XChoice on Americans’ daily time allocation using the American Time Use Survey (ATUS) as human ground truth, revealing heterogeneous alignment across models and activities and salient misalignment concentrated in subgroups defined by race (Black respondents) and marital status (Spouse: Present). We further validate robustness of XChoice via an invariance analysis and evaluate targeted mitigation with a retrieval-augmented generation (RAG) intervention. Overall, XChoice provides mechanism-based metrics that diagnose misalignment beyond surface outcome matching and make the effects of targeted interventions measurable at the mechanism level. Code and data access instructions are available at https://github.com/WeihongQ/xchoice.
%U https://aclanthology.org/2026.findings-aacl.194/
%P 3833-3861
Markdown (Informal)
[XChoice: Explainable Evaluation of AI–Human Alignment in LLM-based Constrained Choice Decision Making](https://aclanthology.org/2026.findings-aacl.194/) (Qi et al., Findings 2026)
ACL