Liu, Y., Moosavi, N.S. orcid.org/0000-0002-8332-307X and Lin, C. (2024) LLMs as narcissistic evaluators: when ego inflates evaluation scores. In: Ku, L-W., Martins, A. and Srikumar, V., (eds.) Findings of the Association for Computational Linguistics: ACL 2024. The 62nd Annual Meeting of the Association for Computational Linguistics, 11-16 Aug 2024, Bangkok, Thailand. Association for Computational Linguistics , pp. 12688-12701.
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.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Editors: |
|
Copyright, Publisher and Additional Information: | © 2024 The Authors. This is an Open Access article distributed under the terms of the Creative Commons Attribution Licence (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 14 Nov 2024 15:01 |
Last Modified: | 14 Nov 2024 15:01 |
Status: | Published |
Publisher: | Association for Computational Linguistics |
Refereed: | Yes |
Identification Number: | 10.18653/v1/2024.findings-acl.753 |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:219671 |