@inproceedings{ferrer-etal-2026-error,
title = "The Error Is the Signal: Misconception Discovery via Step-Error Annotation Clustering",
author = "Ferrer, Robinson Vasquez and
Sachan, Mrinmaya and
Sonkar, Shashank",
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.221/",
pages = "4944--4976",
ISBN = "979-8-89176-439-2",
abstract = "Discovering student misconceptions is a key challenge in intelligent tutoring systems, where identifying recurring error-producing patterns can support targeted feedback and adaptive practice. In settings without a predefined misconception taxonomy, clustering is a natural approach for discovering such patterns at scale. Yet clustering is only as good as its representation: full student records contain problem wording, numerical context, and solution-specific details that embeddings can conflate with the student{'}s error, obscuring the misconception behind the wrong answer. We construct an LLM step-error-annotation-first pipeline that generates step-error annotations, embeds them with or without problem and student response text, and clusters the resulting representations. On MalruleLib, a 101-class misconception benchmark, clustering step-error annotations alone improves clustering accuracy by 0.22 and normalized mutual information by 0.05 on average over clustering the problem and student response, consistent with annotations capturing recurring error patterns more effectively. On Eedi and unlabeled MalAlgoQA, annotation-based representations show higher average held-out clustering accuracy and internal cluster separation, respectively, than their unannotated baselines. To help experts interpret these clusters, the pipeline then generates candidate misconception descriptors and coherence scores for human triage. Overall, these findings show that input representation substantially affects clustering results and that step-error annotations often improve clustering quality."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ferrer-etal-2026-error">
<titleInfo>
<title>The Error Is the Signal: Misconception Discovery via Step-Error Annotation Clustering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Robinson</namePart>
<namePart type="given">Vasquez</namePart>
<namePart type="family">Ferrer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mrinmaya</namePart>
<namePart type="family">Sachan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shashank</namePart>
<namePart type="family">Sonkar</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>Discovering student misconceptions is a key challenge in intelligent tutoring systems, where identifying recurring error-producing patterns can support targeted feedback and adaptive practice. In settings without a predefined misconception taxonomy, clustering is a natural approach for discovering such patterns at scale. Yet clustering is only as good as its representation: full student records contain problem wording, numerical context, and solution-specific details that embeddings can conflate with the student’s error, obscuring the misconception behind the wrong answer. We construct an LLM step-error-annotation-first pipeline that generates step-error annotations, embeds them with or without problem and student response text, and clusters the resulting representations. On MalruleLib, a 101-class misconception benchmark, clustering step-error annotations alone improves clustering accuracy by 0.22 and normalized mutual information by 0.05 on average over clustering the problem and student response, consistent with annotations capturing recurring error patterns more effectively. On Eedi and unlabeled MalAlgoQA, annotation-based representations show higher average held-out clustering accuracy and internal cluster separation, respectively, than their unannotated baselines. To help experts interpret these clusters, the pipeline then generates candidate misconception descriptors and coherence scores for human triage. Overall, these findings show that input representation substantially affects clustering results and that step-error annotations often improve clustering quality.</abstract>
<identifier type="citekey">ferrer-etal-2026-error</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-long.221/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>4944</start>
<end>4976</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Error Is the Signal: Misconception Discovery via Step-Error Annotation Clustering
%A Ferrer, Robinson Vasquez
%A Sachan, Mrinmaya
%A Sonkar, Shashank
%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 ferrer-etal-2026-error
%X Discovering student misconceptions is a key challenge in intelligent tutoring systems, where identifying recurring error-producing patterns can support targeted feedback and adaptive practice. In settings without a predefined misconception taxonomy, clustering is a natural approach for discovering such patterns at scale. Yet clustering is only as good as its representation: full student records contain problem wording, numerical context, and solution-specific details that embeddings can conflate with the student’s error, obscuring the misconception behind the wrong answer. We construct an LLM step-error-annotation-first pipeline that generates step-error annotations, embeds them with or without problem and student response text, and clusters the resulting representations. On MalruleLib, a 101-class misconception benchmark, clustering step-error annotations alone improves clustering accuracy by 0.22 and normalized mutual information by 0.05 on average over clustering the problem and student response, consistent with annotations capturing recurring error patterns more effectively. On Eedi and unlabeled MalAlgoQA, annotation-based representations show higher average held-out clustering accuracy and internal cluster separation, respectively, than their unannotated baselines. To help experts interpret these clusters, the pipeline then generates candidate misconception descriptors and coherence scores for human triage. Overall, these findings show that input representation substantially affects clustering results and that step-error annotations often improve clustering quality.
%U https://aclanthology.org/2026.aacl-long.221/
%P 4944-4976
Markdown (Informal)
[The Error Is the Signal: Misconception Discovery via Step-Error Annotation Clustering](https://aclanthology.org/2026.aacl-long.221/) (Ferrer et al., AACL-IJCNLP 2026)
ACL
- Robinson Vasquez Ferrer, Mrinmaya Sachan, and Shashank Sonkar. 2026. The Error Is the Signal: Misconception Discovery via Step-Error Annotation Clustering. 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 4944–4976, Hengqin, China. Association for Computational Linguistics.