LLMs as Narcissistic Evaluators: When Ego Inflates Evaluation Scores

Yiqi Liu, Nafise Moosavi, Chenghua Lin

Abstract
Automatic evaluation of generated textual content presents an ongoing challenge within the field of NLP. Given the impressive capabilities of modern language models (LMs) across diverse NLP tasks, there is a growing trend to employ these models in creating innovative evaluation metrics for automated assessment of generation tasks. This paper investigates a pivotal question: Do language model-driven evaluation metrics inherently exhibit bias favoring texts generated by the same underlying language model? Specifically, we assess whether prominent LM-based evaluation metrics (e.g. BARTScore, T5Score, and GPTScore) demonstrate a favorable bias toward their respective underlying LMs in the context of summarization tasks. Our findings unveil a latent bias, particularly pronounced when such evaluation metrics are used in a reference-free manner without leveraging gold summaries. These results underscore that assessments provided by generative evaluation models can be influenced by factors beyond the inherent text quality, highlighting the necessity of developing more reliable evaluation protocols in the future.
Anthology ID:
2024.findings-acl.753
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
12688–12701
Language:
URL:
https://preview.aclanthology.org/build-pipeline-with-new-library/2024.findings-acl.753/
DOI:
10.18653/v1/2024.findings-acl.753
Bibkey:
Cite (ACL):
Yiqi Liu, Nafise Moosavi, and Chenghua Lin. 2024. LLMs as Narcissistic Evaluators: When Ego Inflates Evaluation Scores. In Findings of the Association for Computational Linguistics: ACL 2024, pages 12688–12701, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
LLMs as Narcissistic Evaluators: When Ego Inflates Evaluation Scores (Liu et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/build-pipeline-with-new-library/2024.findings-acl.753.pdf
PDF Search