@inproceedings{zhang-etal-2026-misconceptionbench,
title = "{M}isconception{B}ench: Evaluating {LLM}s on Science Misconceptions and Student Response Distributions",
author = "Zhang, Ying and
Wang, Zhaoji and
Zhang, Chenyu and
Gao, Yizhu and
Ma, Wenchao and
Zhai, Xiaoming",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.712/",
pages = "16525--16539",
ISBN = "979-8-89176-459-0",
abstract = "Students' wrong answers in science assessments can reveal plausible misconceptions, yet standard LLM benchmarks usually evaluate only answer correctness. We introduce MisconceptionBench, a benchmark for evaluating whether LLMs can reason about misconception-linked distractors and empirical student response patterns. It contains 761 K-12 science items, 1,474 expert-annotated distractors, and response distributions from more than 150,000 students. We evaluate eight LLMs on three tasks: misconception matching, misconception generation, and student response distribution prediction. In matching, text-similarity baselines remain competitive in two- and three-candidate settings; clear LLM gains emerge only with four candidates, where GPT-4o and Llama-3.3-70B significantly outperform TF-IDF and MiniLM. In generation, the strongest models are tightly clustered, with Hit@1 of 38.5-39.6{\%}, while retrieval-only baselines recover many targets without an LLM. Response distribution prediction remains difficult: no model exceeds F1=0.21 for identifying grade-band differences. Overall, misconception-centered reasoning requires evaluation beyond answer accuracy."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-misconceptionbench">
<titleInfo>
<title>MisconceptionBench: Evaluating LLMs on Science Misconceptions and Student Response Distributions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ying</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhaoji</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenyu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yizhu</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenchao</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoming</namePart>
<namePart type="family">Zhai</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>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Students’ wrong answers in science assessments can reveal plausible misconceptions, yet standard LLM benchmarks usually evaluate only answer correctness. We introduce MisconceptionBench, a benchmark for evaluating whether LLMs can reason about misconception-linked distractors and empirical student response patterns. It contains 761 K-12 science items, 1,474 expert-annotated distractors, and response distributions from more than 150,000 students. We evaluate eight LLMs on three tasks: misconception matching, misconception generation, and student response distribution prediction. In matching, text-similarity baselines remain competitive in two- and three-candidate settings; clear LLM gains emerge only with four candidates, where GPT-4o and Llama-3.3-70B significantly outperform TF-IDF and MiniLM. In generation, the strongest models are tightly clustered, with Hit@1 of 38.5-39.6%, while retrieval-only baselines recover many targets without an LLM. Response distribution prediction remains difficult: no model exceeds F1=0.21 for identifying grade-band differences. Overall, misconception-centered reasoning requires evaluation beyond answer accuracy.</abstract>
<identifier type="citekey">zhang-etal-2026-misconceptionbench</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.712/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>16525</start>
<end>16539</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MisconceptionBench: Evaluating LLMs on Science Misconceptions and Student Response Distributions
%A Zhang, Ying
%A Wang, Zhaoji
%A Zhang, Chenyu
%A Gao, Yizhu
%A Ma, Wenchao
%A Zhai, Xiaoming
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F zhang-etal-2026-misconceptionbench
%X Students’ wrong answers in science assessments can reveal plausible misconceptions, yet standard LLM benchmarks usually evaluate only answer correctness. We introduce MisconceptionBench, a benchmark for evaluating whether LLMs can reason about misconception-linked distractors and empirical student response patterns. It contains 761 K-12 science items, 1,474 expert-annotated distractors, and response distributions from more than 150,000 students. We evaluate eight LLMs on three tasks: misconception matching, misconception generation, and student response distribution prediction. In matching, text-similarity baselines remain competitive in two- and three-candidate settings; clear LLM gains emerge only with four candidates, where GPT-4o and Llama-3.3-70B significantly outperform TF-IDF and MiniLM. In generation, the strongest models are tightly clustered, with Hit@1 of 38.5-39.6%, while retrieval-only baselines recover many targets without an LLM. Response distribution prediction remains difficult: no model exceeds F1=0.21 for identifying grade-band differences. Overall, misconception-centered reasoning requires evaluation beyond answer accuracy.
%U https://aclanthology.org/2026.emnlp-main.712/
%P 16525-16539
Markdown (Informal)
[MisconceptionBench: Evaluating LLMs on Science Misconceptions and Student Response Distributions](https://aclanthology.org/2026.emnlp-main.712/) (Zhang et al., EMNLP 2026)
ACL