@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://preview.aclanthology.org/ingest-acl-workshops/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."
}