Salvato in:
Dettagli Bibliografici
Autori principali: Song, Dan, Lee, Won-Chan, Jiao, Hong
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2507.19980
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909709884194816
author Song, Dan
Lee, Won-Chan
Jiao, Hong
author_facet Song, Dan
Lee, Won-Chan
Jiao, Hong
contents This study investigates the estimation of reliability for large language models (LLMs) in scoring writing tasks from the AP Chinese Language and Culture Exam. Using generalizability theory, the research evaluates and compares score consistency between human and AI raters across two types of AP Chinese free-response writing tasks: story narration and email response. These essays were independently scored by two trained human raters and seven AI raters. Each essay received four scores: one holistic score and three analytic scores corresponding to the domains of task completion, delivery, and language use. Results indicate that although human raters produced more reliable scores overall, LLMs demonstrated reasonable consistency under certain conditions, particularly for story narration tasks. Composite scoring that incorporates both human and AI raters improved reliability, which supports that hybrid scoring models may offer benefits for large-scale writing assessments.
format Preprint
id arxiv_https___arxiv_org_abs_2507_19980
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Exploring LLM Autoscoring Reliability in Large-Scale Writing Assessments Using Generalizability Theory
Song, Dan
Lee, Won-Chan
Jiao, Hong
Computation and Language
This study investigates the estimation of reliability for large language models (LLMs) in scoring writing tasks from the AP Chinese Language and Culture Exam. Using generalizability theory, the research evaluates and compares score consistency between human and AI raters across two types of AP Chinese free-response writing tasks: story narration and email response. These essays were independently scored by two trained human raters and seven AI raters. Each essay received four scores: one holistic score and three analytic scores corresponding to the domains of task completion, delivery, and language use. Results indicate that although human raters produced more reliable scores overall, LLMs demonstrated reasonable consistency under certain conditions, particularly for story narration tasks. Composite scoring that incorporates both human and AI raters improved reliability, which supports that hybrid scoring models may offer benefits for large-scale writing assessments.
title Exploring LLM Autoscoring Reliability in Large-Scale Writing Assessments Using Generalizability Theory
topic Computation and Language
url https://arxiv.org/abs/2507.19980