@inproceedings{tang-etal-2026-test,
title = "From Test-taking to Cognitive Scaffolding: A Pedagogical Diagnostic Benchmark for {LLM}s on {E}nglish Standardized Tests",
author = "Tang, Luoxi and
Sundar, Tharunya and
Meng, Yuqiao and
Yang, Shuai and
Patra, Ankita and
Chippada, Lakshmi Manohar and
Zhao, Jiqian and
Li, Yi and
Ma, Weicheng and
Xi, Zhaohan",
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.149/",
pages = "3433--3470",
ISBN = "979-8-89176-459-0",
abstract = "As large language models (LLMs) are increasingly integrated into educational tools, current evaluations on standardized tests predominantly focus on binary outcome accuracy. Instead, an effective AI tutor must exhibit faithful reasoning, elucidate solution strategies, and diagnose specific human misconceptions. To bridge this gap, we introduce a pedagogical diagnostic framework that models English Standardized Test (EST) problem-solving as a traversal through a cognitive framework. Based on this framework, we present ESTBOOK, a multimodal benchmark encompassing 10,576 questions and 29 task types across five major exams. Unlike traditional datasets, ESTBOOK goes beyond data aggregation by enriching questions with formalized reasoning trajectories and distractor rationales that capture specific cognitive traps. Through extensive evaluations, we show that ESTBOOK identifies fine-grained reasoning bottlenecks and that lightweight mitigation based on these diagnoses provides evidence that the identified failure modes are actionable."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tang-etal-2026-test">
<titleInfo>
<title>From Test-taking to Cognitive Scaffolding: A Pedagogical Diagnostic Benchmark for LLMs on English Standardized Tests</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luoxi</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tharunya</namePart>
<namePart type="family">Sundar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuqiao</namePart>
<namePart type="family">Meng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuai</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ankita</namePart>
<namePart type="family">Patra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lakshmi</namePart>
<namePart type="given">Manohar</namePart>
<namePart type="family">Chippada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiqian</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weicheng</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhaohan</namePart>
<namePart type="family">Xi</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>As large language models (LLMs) are increasingly integrated into educational tools, current evaluations on standardized tests predominantly focus on binary outcome accuracy. Instead, an effective AI tutor must exhibit faithful reasoning, elucidate solution strategies, and diagnose specific human misconceptions. To bridge this gap, we introduce a pedagogical diagnostic framework that models English Standardized Test (EST) problem-solving as a traversal through a cognitive framework. Based on this framework, we present ESTBOOK, a multimodal benchmark encompassing 10,576 questions and 29 task types across five major exams. Unlike traditional datasets, ESTBOOK goes beyond data aggregation by enriching questions with formalized reasoning trajectories and distractor rationales that capture specific cognitive traps. Through extensive evaluations, we show that ESTBOOK identifies fine-grained reasoning bottlenecks and that lightweight mitigation based on these diagnoses provides evidence that the identified failure modes are actionable.</abstract>
<identifier type="citekey">tang-etal-2026-test</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.149/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>3433</start>
<end>3470</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From Test-taking to Cognitive Scaffolding: A Pedagogical Diagnostic Benchmark for LLMs on English Standardized Tests
%A Tang, Luoxi
%A Sundar, Tharunya
%A Meng, Yuqiao
%A Yang, Shuai
%A Patra, Ankita
%A Chippada, Lakshmi Manohar
%A Zhao, Jiqian
%A Li, Yi
%A Ma, Weicheng
%A Xi, Zhaohan
%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 tang-etal-2026-test
%X As large language models (LLMs) are increasingly integrated into educational tools, current evaluations on standardized tests predominantly focus on binary outcome accuracy. Instead, an effective AI tutor must exhibit faithful reasoning, elucidate solution strategies, and diagnose specific human misconceptions. To bridge this gap, we introduce a pedagogical diagnostic framework that models English Standardized Test (EST) problem-solving as a traversal through a cognitive framework. Based on this framework, we present ESTBOOK, a multimodal benchmark encompassing 10,576 questions and 29 task types across five major exams. Unlike traditional datasets, ESTBOOK goes beyond data aggregation by enriching questions with formalized reasoning trajectories and distractor rationales that capture specific cognitive traps. Through extensive evaluations, we show that ESTBOOK identifies fine-grained reasoning bottlenecks and that lightweight mitigation based on these diagnoses provides evidence that the identified failure modes are actionable.
%U https://aclanthology.org/2026.emnlp-main.149/
%P 3433-3470
Markdown (Informal)
[From Test-taking to Cognitive Scaffolding: A Pedagogical Diagnostic Benchmark for LLMs on English Standardized Tests](https://aclanthology.org/2026.emnlp-main.149/) (Tang et al., EMNLP 2026)
ACL
- Luoxi Tang, Tharunya Sundar, Yuqiao Meng, Shuai Yang, Ankita Patra, Lakshmi Manohar Chippada, Jiqian Zhao, Yi Li, Weicheng Ma, and Zhaohan Xi. 2026. From Test-taking to Cognitive Scaffolding: A Pedagogical Diagnostic Benchmark for LLMs on English Standardized Tests. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 3433–3470, Budapest, Hungary. Association for Computational Linguistics.