How Model Size, Temperature, and Prompt Style Affect LLM-Human Assessment Score Alignment

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Jung, Julie, Lu, Max, Benker, Sina Chole, Darici, Dogus
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914052650827776
author Jung, Julie
Lu, Max
Benker, Sina Chole
Darici, Dogus
author_facet Jung, Julie
Lu, Max
Benker, Sina Chole
Darici, Dogus
contents We examined how model size, temperature, and prompt style affect Large Language Models' (LLMs) alignment within itself, between models, and with human in assessing clinical reasoning skills. Model size emerged as a key factor in LLM-human score alignment. Study highlights the importance of checking alignments across multiple levels.
format Preprint
id arxiv_https___arxiv_org_abs_2509_19329
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle How Model Size, Temperature, and Prompt Style Affect LLM-Human Assessment Score Alignment
Jung, Julie
Lu, Max
Benker, Sina Chole
Darici, Dogus
Computation and Language
Methodology
We examined how model size, temperature, and prompt style affect Large Language Models' (LLMs) alignment within itself, between models, and with human in assessing clinical reasoning skills. Model size emerged as a key factor in LLM-human score alignment. Study highlights the importance of checking alignments across multiple levels.
title How Model Size, Temperature, and Prompt Style Affect LLM-Human Assessment Score Alignment
topic Computation and Language
Methodology
url https://arxiv.org/abs/2509.19329