@inproceedings{lee-etal-2026-questions,
title = "Which Questions Improve Learning the Most? Utility Estimation of Questions with {LM}-based Simulations",
author = "Lee, Dong-Ho and
Cho, Hyundong Justin and
May, Jonathan and
Pujara, Jay",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.97/",
pages = "2015--2034",
ISBN = "979-8-89176-462-0",
abstract = "Asking questions is fundamental for deeper understanding, yet evaluating and generating questions that improve downstream outcomes remains a challenging problem. To address this gap, we introduce QUEST (Question Utility Estimation with Simulated Tests), a framework that offers a new outcome-driven paradigm for question evaluation and generation, instead of indirect metrics that are based on the underlying content of the question and its answer. QUEST uses language models to simulate learners that ask questions while studying a textbook chapter and quantifies the utility of a question as its direct contribution to understanding as measured by the learner{'}s exam performance. To analyze the effectiveness of QUEST, we curate TEXTBOOK-EXAM, a benchmark that aligns textbook sections with exam questions across five academic disciplines. Using QUEST, we filter for high-utility questions and fine-tune question generators via rejection sampling and show that questions generated by QUEST-trained models improve simulated exam scores by 19.6{\%} compared to the next strongest baseline. Furthermore, we demonstrate the practical real-world value of QUEST by showing that simulation-computed utility of a question is moderately positively correlated with its usefulness as perceived by human evaluators."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-etal-2026-questions">
<titleInfo>
<title>Which Questions Improve Learning the Most? Utility Estimation of Questions with LM-based Simulations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dong-Ho</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyundong</namePart>
<namePart type="given">Justin</namePart>
<namePart type="family">Cho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">May</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jay</namePart>
<namePart type="family">Pujara</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>Asking questions is fundamental for deeper understanding, yet evaluating and generating questions that improve downstream outcomes remains a challenging problem. To address this gap, we introduce QUEST (Question Utility Estimation with Simulated Tests), a framework that offers a new outcome-driven paradigm for question evaluation and generation, instead of indirect metrics that are based on the underlying content of the question and its answer. QUEST uses language models to simulate learners that ask questions while studying a textbook chapter and quantifies the utility of a question as its direct contribution to understanding as measured by the learner’s exam performance. To analyze the effectiveness of QUEST, we curate TEXTBOOK-EXAM, a benchmark that aligns textbook sections with exam questions across five academic disciplines. Using QUEST, we filter for high-utility questions and fine-tune question generators via rejection sampling and show that questions generated by QUEST-trained models improve simulated exam scores by 19.6% compared to the next strongest baseline. Furthermore, we demonstrate the practical real-world value of QUEST by showing that simulation-computed utility of a question is moderately positively correlated with its usefulness as perceived by human evaluators.</abstract>
<identifier type="citekey">lee-etal-2026-questions</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.97/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>2015</start>
<end>2034</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Which Questions Improve Learning the Most? Utility Estimation of Questions with LM-based Simulations
%A Lee, Dong-Ho
%A Cho, Hyundong Justin
%A May, Jonathan
%A Pujara, Jay
%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 lee-etal-2026-questions
%X Asking questions is fundamental for deeper understanding, yet evaluating and generating questions that improve downstream outcomes remains a challenging problem. To address this gap, we introduce QUEST (Question Utility Estimation with Simulated Tests), a framework that offers a new outcome-driven paradigm for question evaluation and generation, instead of indirect metrics that are based on the underlying content of the question and its answer. QUEST uses language models to simulate learners that ask questions while studying a textbook chapter and quantifies the utility of a question as its direct contribution to understanding as measured by the learner’s exam performance. To analyze the effectiveness of QUEST, we curate TEXTBOOK-EXAM, a benchmark that aligns textbook sections with exam questions across five academic disciplines. Using QUEST, we filter for high-utility questions and fine-tune question generators via rejection sampling and show that questions generated by QUEST-trained models improve simulated exam scores by 19.6% compared to the next strongest baseline. Furthermore, we demonstrate the practical real-world value of QUEST by showing that simulation-computed utility of a question is moderately positively correlated with its usefulness as perceived by human evaluators.
%U https://aclanthology.org/2026.findings-emnlp.97/
%P 2015-2034
Markdown (Informal)
[Which Questions Improve Learning the Most? Utility Estimation of Questions with LM-based Simulations](https://aclanthology.org/2026.findings-emnlp.97/) (Lee et al., Findings 2026)
ACL