@inproceedings{hardy-2025-measuring,
title = "Measuring Teaching with {LLM}s",
author = "Hardy, Michael",
editor = "Wilson, Joshua and
Ormerod, Christopher and
Beiting Parrish, Magdalen",
booktitle = "Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers",
month = oct,
year = "2025",
address = "Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States",
publisher = "National Council on Measurement in Education (NCME)",
url = "https://aclanthology.org/2025.aimecon-main.40/",
pages = "367--384",
ISBN = "979-8-218-84228-4",
abstract = "This paper introduces custom Large Language Models using sentence-level embeddings to measure teaching quality. The models achieve human-level performance in analyzing classroom transcripts, outperforming average human rater correlation. Aggregate model scores align with student learning outcomes, establishing a powerful new methodology for scalable teacher feedback. Important limitations discussed."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hardy-2025-measuring">
<titleInfo>
<title>Measuring Teaching with LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Hardy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joshua</namePart>
<namePart type="family">Wilson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Ormerod</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Magdalen</namePart>
<namePart type="family">Beiting Parrish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>National Council on Measurement in Education (NCME)</publisher>
<place>
<placeTerm type="text">Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-218-84228-4</identifier>
</relatedItem>
<abstract>This paper introduces custom Large Language Models using sentence-level embeddings to measure teaching quality. The models achieve human-level performance in analyzing classroom transcripts, outperforming average human rater correlation. Aggregate model scores align with student learning outcomes, establishing a powerful new methodology for scalable teacher feedback. Important limitations discussed.</abstract>
<identifier type="citekey">hardy-2025-measuring</identifier>
<location>
<url>https://aclanthology.org/2025.aimecon-main.40/</url>
</location>
<part>
<date>2025-10</date>
<extent unit="page">
<start>367</start>
<end>384</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Measuring Teaching with LLMs
%A Hardy, Michael
%Y Wilson, Joshua
%Y Ormerod, Christopher
%Y Beiting Parrish, Magdalen
%S Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers
%D 2025
%8 October
%I National Council on Measurement in Education (NCME)
%C Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States
%@ 979-8-218-84228-4
%F hardy-2025-measuring
%X This paper introduces custom Large Language Models using sentence-level embeddings to measure teaching quality. The models achieve human-level performance in analyzing classroom transcripts, outperforming average human rater correlation. Aggregate model scores align with student learning outcomes, establishing a powerful new methodology for scalable teacher feedback. Important limitations discussed.
%U https://aclanthology.org/2025.aimecon-main.40/
%P 367-384
Markdown (Informal)
[Measuring Teaching with LLMs](https://aclanthology.org/2025.aimecon-main.40/) (Hardy, AIME-Con 2025)
ACL
- Michael Hardy. 2025. Measuring Teaching with LLMs. In Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers, pages 367–384, Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States. National Council on Measurement in Education (NCME).