跳到正文
arXiv cs.AI· Manzanarez Gerardo Aleman, Monroy Raul, Garcia Flores Jorge, Calvo Hiram·· 56 分钟前AI 评分31

LLM 能否评价文学作品?用大语言模型在 GrAImes 框架中筛选小说

Literary Language Mashup: Curating Fictions with Large Language Models

AI 导读

研究者在 GrAImes 框架中用 LLM 充当文学评价者,评估西班牙语微型小说、英西双语短篇小说,并与 5 位文学博士教授和 16 位文学爱好者的评分对比。结果显示 LLM 与人类评委的 Krippendorff's alpha 系数低于 0.66,不能替代人类评委,但可作为评估文本编辑质量的辅助工具。

正文 · 原文

View PDF

Abstract:In this paper, we propose an alternative approach to human evaluation of literary fictions by employing LLMs themselves as evaluators within the GrAImes framework. We apply this methodology to assess human-written and AI-generated microfictions in Spanish, to five PhD professors in literature and sixteen literary enthusiasts, and to short stories in both Spanish and English. By comparing the evaluations performed by LLMs with those of human judges, we examine the degree of alignment and divergence between both perspectives, thereby assessing the feasibility of LLMs as auxiliary literary evaluators. Our analysis focuses on the alignment of responses from LLMs with those of human evaluators, providing insights into the potential of LLMs in literary assessment. The conducted experiments reveal that while LLMs cannot be regarded as substitutes for human judges in the evaluation of literary microfictions and short stories, with a Krippendorff's alpha reliability coefficient less than 0.66, they can serve as a valuable tool that offers an initial perspective on the editorial quality of the texts in question. Overall, this study contributes to the ongoing discourse on the role of artificial intelligence in literature, underlining both its methodological constraints and its potential as a complementary resource for literary evaluation.
Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
Cite as: arXiv:2611.21649 [cs.CL]
  (or arXiv:2611.21649v1 [cs.CL] for this version)
  https://doi.org/10.48550/arXiv.2611.21649

arXiv-issued DOI via DataCite (pending registration)

Journal reference: Mathematics 2025, 1, 0
Related DOI: https://doi.org/10.3390/math1010000

DOI(s) linking to related resources

Submission history

From: Gerardo Aleman Manzanarez [view email]
[v1] Thu, 15 Oct 2026 01:43:14 UTC (2,823 KB)

来源:arXiv cs.AI · arxiv.org