Enregistré dans:
Détails bibliographiques
Auteurs principaux: Kim, Seungyoon, Kim, Seungone
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2407.17022
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916334988689408
author Kim, Seungyoon
Kim, Seungone
author_facet Kim, Seungyoon
Kim, Seungone
contents Large language model (LLM)-based evaluation pipelines have demonstrated their capability to robustly evaluate machine-generated text. Extending this methodology to assess human-written text could significantly benefit educational settings by providing direct feedback to enhance writing skills, although this application is not straightforward. In this paper, we investigate whether LLMs can effectively assess human-written text for educational purposes. We collected 100 texts from 32 Korean students across 15 types of writing and employed GPT-4-Turbo to evaluate them using grammaticality, fluency, coherence, consistency, and relevance as criteria. Our analyses indicate that LLM evaluators can reliably assess grammaticality and fluency, as well as more objective types of writing, though they struggle with other criteria and types of writing. We publicly release our dataset and feedback.
format Preprint
id arxiv_https___arxiv_org_abs_2407_17022
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Can Language Models Evaluate Human Written Text? Case Study on Korean Student Writing for Education
Kim, Seungyoon
Kim, Seungone
Computation and Language
Large language model (LLM)-based evaluation pipelines have demonstrated their capability to robustly evaluate machine-generated text. Extending this methodology to assess human-written text could significantly benefit educational settings by providing direct feedback to enhance writing skills, although this application is not straightforward. In this paper, we investigate whether LLMs can effectively assess human-written text for educational purposes. We collected 100 texts from 32 Korean students across 15 types of writing and employed GPT-4-Turbo to evaluate them using grammaticality, fluency, coherence, consistency, and relevance as criteria. Our analyses indicate that LLM evaluators can reliably assess grammaticality and fluency, as well as more objective types of writing, though they struggle with other criteria and types of writing. We publicly release our dataset and feedback.
title Can Language Models Evaluate Human Written Text? Case Study on Korean Student Writing for Education
topic Computation and Language
url https://arxiv.org/abs/2407.17022