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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jung, Julie, Lu, Max, Benker, Sina Chole, Darici, Dogus
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Methodology
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2509.19329