@inproceedings{lee-etal-2026-misconceptdialogue,
title = "{M}isconcept{D}ialogue: Evaluation Criteria Shape Measured Success in {LLM} Math Tutoring",
author = "Lee, Woojin and
Woo, Yoonkyu and
Kim, Jinah and
Gwon, Hyeok-Min and
Huang, Jin-Xia",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.aacl-long.112/",
pages = "2454--2473",
ISBN = "979-8-89176-439-2",
abstract = "Large language models are increasingly used as math tutors, raising two questions: can a single LLM detect a student{'}s error, diagnose the underlying misconception, and remediate it through multi-turn dialogue{---}and can we trust the numbers that report how well it does? We address both with MisconceptDialogue, a fully automated framework that runs the full pipeline on five open-weight LLM tutors (7B{--}14B) interacting with LLM-simulated students over 5,000+ dialogues{---}a deliberately simulated protocol (paired conditions, a wrong-diagnosis control unsafe with real learners, scale) whose results do not establish real-student learning. On measurement, our headline finding is uncomfortable for the field: benchmark-style exact-match scoring common in standard math NLP{---}a lower-bound stress test{---}reports 42.1{\%} measured Remediation Success Rate on identical dialogues where a human-calibrated LLM-as-judge reports 81.3{\%}, a 39.2 percentage-point spread larger than the combined effects of tutor model, teaching strategy, and supplied diagnostic information. This is not a single-judge artifact: four independent LLM judges and 200 human annotations converge to within a few points ({\ensuremath{\kappa}} up to 0.91). On capability, the verdict is equally striking: the score barely changes whether we tell the tutor the student{'}s actual misconception or a deliberately swapped one{---}under the tested diagnosis-presentation format, these tutors show little evidence of reliably conditioning on the diagnostic information they are handed. For LLM tutoring evaluation to mature, multi-criterion scoring with multi-judge convergence and human anchoring should become standard practice{---}and the measurement question deserves as much scrutiny as the capability question it claims to answer."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-etal-2026-misconceptdialogue">
<titleInfo>
<title>MisconceptDialogue: Evaluation Criteria Shape Measured Success in LLM Math Tutoring</title>
</titleInfo>
<name type="personal">
<namePart type="given">Woojin</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoonkyu</namePart>
<namePart type="family">Woo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinah</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyeok-Min</namePart>
<namePart type="family">Gwon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jin-Xia</namePart>
<namePart type="family">Huang</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>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</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">979-8-89176-439-2</identifier>
</relatedItem>
<abstract>Large language models are increasingly used as math tutors, raising two questions: can a single LLM detect a student’s error, diagnose the underlying misconception, and remediate it through multi-turn dialogue—and can we trust the numbers that report how well it does? We address both with MisconceptDialogue, a fully automated framework that runs the full pipeline on five open-weight LLM tutors (7B–14B) interacting with LLM-simulated students over 5,000+ dialogues—a deliberately simulated protocol (paired conditions, a wrong-diagnosis control unsafe with real learners, scale) whose results do not establish real-student learning. On measurement, our headline finding is uncomfortable for the field: benchmark-style exact-match scoring common in standard math NLP—a lower-bound stress test—reports 42.1% measured Remediation Success Rate on identical dialogues where a human-calibrated LLM-as-judge reports 81.3%, a 39.2 percentage-point spread larger than the combined effects of tutor model, teaching strategy, and supplied diagnostic information. This is not a single-judge artifact: four independent LLM judges and 200 human annotations converge to within a few points (\ensuremathąppa up to 0.91). On capability, the verdict is equally striking: the score barely changes whether we tell the tutor the student’s actual misconception or a deliberately swapped one—under the tested diagnosis-presentation format, these tutors show little evidence of reliably conditioning on the diagnostic information they are handed. For LLM tutoring evaluation to mature, multi-criterion scoring with multi-judge convergence and human anchoring should become standard practice—and the measurement question deserves as much scrutiny as the capability question it claims to answer.</abstract>
<identifier type="citekey">lee-etal-2026-misconceptdialogue</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-long.112/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>2454</start>
<end>2473</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MisconceptDialogue: Evaluation Criteria Shape Measured Success in LLM Math Tutoring
%A Lee, Woojin
%A Woo, Yoonkyu
%A Kim, Jinah
%A Gwon, Hyeok-Min
%A Huang, Jin-Xia
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-439-2
%F lee-etal-2026-misconceptdialogue
%X Large language models are increasingly used as math tutors, raising two questions: can a single LLM detect a student’s error, diagnose the underlying misconception, and remediate it through multi-turn dialogue—and can we trust the numbers that report how well it does? We address both with MisconceptDialogue, a fully automated framework that runs the full pipeline on five open-weight LLM tutors (7B–14B) interacting with LLM-simulated students over 5,000+ dialogues—a deliberately simulated protocol (paired conditions, a wrong-diagnosis control unsafe with real learners, scale) whose results do not establish real-student learning. On measurement, our headline finding is uncomfortable for the field: benchmark-style exact-match scoring common in standard math NLP—a lower-bound stress test—reports 42.1% measured Remediation Success Rate on identical dialogues where a human-calibrated LLM-as-judge reports 81.3%, a 39.2 percentage-point spread larger than the combined effects of tutor model, teaching strategy, and supplied diagnostic information. This is not a single-judge artifact: four independent LLM judges and 200 human annotations converge to within a few points (\ensuremathąppa up to 0.91). On capability, the verdict is equally striking: the score barely changes whether we tell the tutor the student’s actual misconception or a deliberately swapped one—under the tested diagnosis-presentation format, these tutors show little evidence of reliably conditioning on the diagnostic information they are handed. For LLM tutoring evaluation to mature, multi-criterion scoring with multi-judge convergence and human anchoring should become standard practice—and the measurement question deserves as much scrutiny as the capability question it claims to answer.
%U https://aclanthology.org/2026.aacl-long.112/
%P 2454-2473
Markdown (Informal)
[MisconceptDialogue: Evaluation Criteria Shape Measured Success in LLM Math Tutoring](https://aclanthology.org/2026.aacl-long.112/) (Lee et al., AACL-IJCNLP 2026)
ACL
- Woojin Lee, Yoonkyu Woo, Jinah Kim, Hyeok-Min Gwon, and Jin-Xia Huang. 2026. MisconceptDialogue: Evaluation Criteria Shape Measured Success in LLM Math Tutoring. In Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2454–2473, Hengqin, China. Association for Computational Linguistics.