Can Large Language Models Outperform Non-Experts in Poetry Evaluation? A Comparative Study Using the Consensual Assessment Technique

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sawicki, Piotr, Grześ, Marek, Brown, Dan, Góes, Fabrício
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916989026435072
author Sawicki, Piotr
Grześ, Marek
Brown, Dan
Góes, Fabrício
author_facet Sawicki, Piotr
Grześ, Marek
Brown, Dan
Góes, Fabrício
contents This study adapts the Consensual Assessment Technique (CAT) for Large Language Models (LLMs), introducing a novel methodology for poetry evaluation. Using a 90-poem dataset with a ground truth based on publication venue, we demonstrate that this approach allows LLMs to significantly surpass the performance of non-expert human judges. Our method, which leverages forced-choice ranking within small, randomized batches, enabled Claude-3-Opus to achieve a Spearman's Rank Correlation of 0.87 with the ground truth, dramatically outperforming the best human non-expert evaluation (SRC = 0.38). The LLM assessments also exhibited high inter-rater reliability, underscoring the methodology's robustness. These findings establish that LLMs, when guided by a comparative framework, can be effective and reliable tools for assessing poetry, paving the way for their broader application in other creative domains.
format Preprint
id arxiv_https___arxiv_org_abs_2502_19064
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Can Large Language Models Outperform Non-Experts in Poetry Evaluation? A Comparative Study Using the Consensual Assessment Technique
Sawicki, Piotr
Grześ, Marek
Brown, Dan
Góes, Fabrício
Computation and Language
This study adapts the Consensual Assessment Technique (CAT) for Large Language Models (LLMs), introducing a novel methodology for poetry evaluation. Using a 90-poem dataset with a ground truth based on publication venue, we demonstrate that this approach allows LLMs to significantly surpass the performance of non-expert human judges. Our method, which leverages forced-choice ranking within small, randomized batches, enabled Claude-3-Opus to achieve a Spearman's Rank Correlation of 0.87 with the ground truth, dramatically outperforming the best human non-expert evaluation (SRC = 0.38). The LLM assessments also exhibited high inter-rater reliability, underscoring the methodology's robustness. These findings establish that LLMs, when guided by a comparative framework, can be effective and reliable tools for assessing poetry, paving the way for their broader application in other creative domains.
title Can Large Language Models Outperform Non-Experts in Poetry Evaluation? A Comparative Study Using the Consensual Assessment Technique
topic Computation and Language
url https://arxiv.org/abs/2502.19064