@inproceedings{jung-etal-2025-model,
title = "How Model Size, Temperature, and Prompt Style Affect {LLM}-Human Assessment Score Alignment",
author = "Jung, Julie and
Lu, Max and
Benker, Sina Chole and
Darici, Dogus",
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.28/",
pages = "265--273",
ISBN = "979-8-218-84228-4",
abstract = "We examined how model size, temperature, and prompt style affect Large Language Models' (LLMs) alignment with human raters in assessing clinical reasoning skills. Model size emerged as a key factor in LLM-human score alignment. Findings reveal both the potential for scalable LLM-raters and the risks of relying on them exclusively."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jung-etal-2025-model">
<titleInfo>
<title>How Model Size, Temperature, and Prompt Style Affect LLM-Human Assessment Score Alignment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Julie</namePart>
<namePart type="family">Jung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Max</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sina</namePart>
<namePart type="given">Chole</namePart>
<namePart type="family">Benker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dogus</namePart>
<namePart type="family">Darici</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>We examined how model size, temperature, and prompt style affect Large Language Models’ (LLMs) alignment with human raters in assessing clinical reasoning skills. Model size emerged as a key factor in LLM-human score alignment. Findings reveal both the potential for scalable LLM-raters and the risks of relying on them exclusively.</abstract>
<identifier type="citekey">jung-etal-2025-model</identifier>
<location>
<url>https://aclanthology.org/2025.aimecon-main.28/</url>
</location>
<part>
<date>2025-10</date>
<extent unit="page">
<start>265</start>
<end>273</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How Model Size, Temperature, and Prompt Style Affect LLM-Human Assessment Score Alignment
%A Jung, Julie
%A Lu, Max
%A Benker, Sina Chole
%A Darici, Dogus
%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 jung-etal-2025-model
%X We examined how model size, temperature, and prompt style affect Large Language Models’ (LLMs) alignment with human raters in assessing clinical reasoning skills. Model size emerged as a key factor in LLM-human score alignment. Findings reveal both the potential for scalable LLM-raters and the risks of relying on them exclusively.
%U https://aclanthology.org/2025.aimecon-main.28/
%P 265-273
Markdown (Informal)
[How Model Size, Temperature, and Prompt Style Affect LLM-Human Assessment Score Alignment](https://aclanthology.org/2025.aimecon-main.28/) (Jung et al., AIME-Con 2025)
ACL
- Julie Jung, Max Lu, Sina Chole Benker, and Dogus Darici. 2025. How Model Size, Temperature, and Prompt Style Affect LLM-Human Assessment Score Alignment. In Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Full Papers, pages 265–273, Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States. National Council on Measurement in Education (NCME).