@inproceedings{mahajan-etal-2026-mind,
title = "Mind the Gap: How Elicitation Protocols Shape the Stated-Revealed Preference Gap in Language Models",
author = "Mahajan, Pranav and
Kendiukhov, Ihor and
Hussain, Syed and
Nottingham, Lydia",
editor = "Akhtar, Mubashara and
Batzner, Jan and
Choshen, Leshem and
Ghosh, Avijit and
Gohar, Usman and
Mickel, Jennifer and
Pant, Ichhya and
Talat, Zeerak and
Lin, Michelle",
booktitle = "Proceedings of the Workshop on Evaluating Evaluations ({E}val{E}val)",
month = jul,
year = "2026",
address = "San Diego, CA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.evaleval-1.9/",
pages = "46--55",
ISBN = "979-8-89176-429-3",
abstract = "Recent work identifies a stated{--}revealed (SvR) preference gap in language models (LMs): a mismatch between the values models endorse and the choices they make in context. Existing evaluations rely heavily on binary forcedchoice prompting, which entangles genuine preferences with artifacts of the elicitation protocol. We systematically study how elicitation protocols affect SvR correlation across 24 LMs. Allowing neutrality and abstention during stated preference elicitation allows us to exclude weak signals, substantially improving Spearman{'}s rank correlation ({\ensuremath{\rho}}) between volunteered stated preferences and forced-choice revealed preferences. However, further allowing abstention in revealed preferences drives {\ensuremath{\rho}} to near-zero or negative values due to high neutrality rates. Finally, we find that system prompt steering using stated preferences during revealed preference elicitation does not reliably improve SvR correlation on AIRiskDilemmas. Together, our results show that SvR correlation is highly protocol-dependent and that preference elicitation requires methods that account for indeterminate preferences."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mahajan-etal-2026-mind">
<titleInfo>
<title>Mind the Gap: How Elicitation Protocols Shape the Stated-Revealed Preference Gap in Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pranav</namePart>
<namePart type="family">Mahajan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ihor</namePart>
<namePart type="family">Kendiukhov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Syed</namePart>
<namePart type="family">Hussain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lydia</namePart>
<namePart type="family">Nottingham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Evaluating Evaluations (EvalEval)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mubashara</namePart>
<namePart type="family">Akhtar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Batzner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leshem</namePart>
<namePart type="family">Choshen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Avijit</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Usman</namePart>
<namePart type="family">Gohar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jennifer</namePart>
<namePart type="family">Mickel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ichhya</namePart>
<namePart type="family">Pant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zeerak</namePart>
<namePart type="family">Talat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michelle</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, CA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-429-3</identifier>
</relatedItem>
<abstract>Recent work identifies a stated–revealed (SvR) preference gap in language models (LMs): a mismatch between the values models endorse and the choices they make in context. Existing evaluations rely heavily on binary forcedchoice prompting, which entangles genuine preferences with artifacts of the elicitation protocol. We systematically study how elicitation protocols affect SvR correlation across 24 LMs. Allowing neutrality and abstention during stated preference elicitation allows us to exclude weak signals, substantially improving Spearman’s rank correlation (\ensuremathρ) between volunteered stated preferences and forced-choice revealed preferences. However, further allowing abstention in revealed preferences drives \ensuremathρ to near-zero or negative values due to high neutrality rates. Finally, we find that system prompt steering using stated preferences during revealed preference elicitation does not reliably improve SvR correlation on AIRiskDilemmas. Together, our results show that SvR correlation is highly protocol-dependent and that preference elicitation requires methods that account for indeterminate preferences.</abstract>
<identifier type="citekey">mahajan-etal-2026-mind</identifier>
<location>
<url>https://aclanthology.org/2026.evaleval-1.9/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>46</start>
<end>55</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mind the Gap: How Elicitation Protocols Shape the Stated-Revealed Preference Gap in Language Models
%A Mahajan, Pranav
%A Kendiukhov, Ihor
%A Hussain, Syed
%A Nottingham, Lydia
%Y Akhtar, Mubashara
%Y Batzner, Jan
%Y Choshen, Leshem
%Y Ghosh, Avijit
%Y Gohar, Usman
%Y Mickel, Jennifer
%Y Pant, Ichhya
%Y Talat, Zeerak
%Y Lin, Michelle
%S Proceedings of the Workshop on Evaluating Evaluations (EvalEval)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, CA
%@ 979-8-89176-429-3
%F mahajan-etal-2026-mind
%X Recent work identifies a stated–revealed (SvR) preference gap in language models (LMs): a mismatch between the values models endorse and the choices they make in context. Existing evaluations rely heavily on binary forcedchoice prompting, which entangles genuine preferences with artifacts of the elicitation protocol. We systematically study how elicitation protocols affect SvR correlation across 24 LMs. Allowing neutrality and abstention during stated preference elicitation allows us to exclude weak signals, substantially improving Spearman’s rank correlation (\ensuremathρ) between volunteered stated preferences and forced-choice revealed preferences. However, further allowing abstention in revealed preferences drives \ensuremathρ to near-zero or negative values due to high neutrality rates. Finally, we find that system prompt steering using stated preferences during revealed preference elicitation does not reliably improve SvR correlation on AIRiskDilemmas. Together, our results show that SvR correlation is highly protocol-dependent and that preference elicitation requires methods that account for indeterminate preferences.
%U https://aclanthology.org/2026.evaleval-1.9/
%P 46-55
Markdown (Informal)
[Mind the Gap: How Elicitation Protocols Shape the Stated-Revealed Preference Gap in Language Models](https://aclanthology.org/2026.evaleval-1.9/) (Mahajan et al., EvalEval 2026)
ACL