@inproceedings{zahid-etal-2026-quantitative,
title = "A Quantitative Gap Audit of {LLM}-era {NLP} for Education: Validity, Deployment, and Multilingual Equity",
author = "Zahid, Farzana and
Islam, Md. Rakibul and
Kader, Mayesha and
Anika, Israt Jahan",
editor = "Atwell, Katherine and
Borah, Angana and
Dementieva, Daryna and
Kreiss, Elisa and
Kotonya, Neema and
Liu, Jiarui and
Olson, Liz and
Wan, Ruyuan and
Zhao, Jieyu",
booktitle = "Proceedings of the Fifth Workshop on {NLP} for Positive Impact ({NLP}4{PI})",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.nlp4pi-1.1/",
pages = "1--16",
ISBN = "979-8-89176-495-8",
abstract = "It remains unclear whether LLM capabil- ity gains translate into measurable student learning. We analyze 137 educational NLP papers (2022{--}2025) across four sectors{---} assessment and grammatical error correc- tion, feedback and writing support, content and question generation, and tutoring and dialogue{---}introducing three metrics: Valid- ity Gap (VG, share of studies not evaluat- ing learning outcomes), Deployment Readi- ness Index (DRI, real-world evaluation ex- tent), and Multilingual Equity Index (MEI, language coverage). We find a high validity gap (VG = 0.927), low deployment readiness (DRI = 0.126), and limited multilingual cov- erage (MEI = 0.126); grammatical error cor- rection shows no learning-improvement evi- dence at all (VG = 1.000). DRI correlates with learning-outcome evaluation ({\ensuremath{\rho}} = 0.425, p {\ensuremath{<}} 0.001). Our taxonomy and metrics offer the first quantitative audit of educational NLP in the LLM era."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zahid-etal-2026-quantitative">
<titleInfo>
<title>A Quantitative Gap Audit of LLM-era NLP for Education: Validity, Deployment, and Multilingual Equity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Farzana</namePart>
<namePart type="family">Zahid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Rakibul</namePart>
<namePart type="family">Islam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mayesha</namePart>
<namePart type="family">Kader</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Israt</namePart>
<namePart type="given">Jahan</namePart>
<namePart type="family">Anika</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 Fifth Workshop on NLP for Positive Impact (NLP4PI)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Katherine</namePart>
<namePart type="family">Atwell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angana</namePart>
<namePart type="family">Borah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daryna</namePart>
<namePart type="family">Dementieva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elisa</namePart>
<namePart type="family">Kreiss</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Neema</namePart>
<namePart type="family">Kotonya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiarui</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liz</namePart>
<namePart type="family">Olson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruyuan</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jieyu</namePart>
<namePart type="family">Zhao</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">979-8-89176-495-8</identifier>
</relatedItem>
<abstract>It remains unclear whether LLM capabil- ity gains translate into measurable student learning. We analyze 137 educational NLP papers (2022–2025) across four sectors— assessment and grammatical error correc- tion, feedback and writing support, content and question generation, and tutoring and dialogue—introducing three metrics: Valid- ity Gap (VG, share of studies not evaluat- ing learning outcomes), Deployment Readi- ness Index (DRI, real-world evaluation ex- tent), and Multilingual Equity Index (MEI, language coverage). We find a high validity gap (VG = 0.927), low deployment readiness (DRI = 0.126), and limited multilingual cov- erage (MEI = 0.126); grammatical error cor- rection shows no learning-improvement evi- dence at all (VG = 1.000). DRI correlates with learning-outcome evaluation (\ensuremathρ = 0.425, p \ensuremath< 0.001). Our taxonomy and metrics offer the first quantitative audit of educational NLP in the LLM era.</abstract>
<identifier type="citekey">zahid-etal-2026-quantitative</identifier>
<location>
<url>https://aclanthology.org/2026.nlp4pi-1.1/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1</start>
<end>16</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Quantitative Gap Audit of LLM-era NLP for Education: Validity, Deployment, and Multilingual Equity
%A Zahid, Farzana
%A Islam, Md. Rakibul
%A Kader, Mayesha
%A Anika, Israt Jahan
%Y Atwell, Katherine
%Y Borah, Angana
%Y Dementieva, Daryna
%Y Kreiss, Elisa
%Y Kotonya, Neema
%Y Liu, Jiarui
%Y Olson, Liz
%Y Wan, Ruyuan
%Y Zhao, Jieyu
%S Proceedings of the Fifth Workshop on NLP for Positive Impact (NLP4PI)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-495-8
%F zahid-etal-2026-quantitative
%X It remains unclear whether LLM capabil- ity gains translate into measurable student learning. We analyze 137 educational NLP papers (2022–2025) across four sectors— assessment and grammatical error correc- tion, feedback and writing support, content and question generation, and tutoring and dialogue—introducing three metrics: Valid- ity Gap (VG, share of studies not evaluat- ing learning outcomes), Deployment Readi- ness Index (DRI, real-world evaluation ex- tent), and Multilingual Equity Index (MEI, language coverage). We find a high validity gap (VG = 0.927), low deployment readiness (DRI = 0.126), and limited multilingual cov- erage (MEI = 0.126); grammatical error cor- rection shows no learning-improvement evi- dence at all (VG = 1.000). DRI correlates with learning-outcome evaluation (\ensuremathρ = 0.425, p \ensuremath< 0.001). Our taxonomy and metrics offer the first quantitative audit of educational NLP in the LLM era.
%U https://aclanthology.org/2026.nlp4pi-1.1/
%P 1-16
Markdown (Informal)
[A Quantitative Gap Audit of LLM-era NLP for Education: Validity, Deployment, and Multilingual Equity](https://aclanthology.org/2026.nlp4pi-1.1/) (Zahid et al., NLP4PI 2026)
ACL