A Novel Metric for Measuring the Robustness of Large Language Models in Non-adversarial Scenarios

Samuel Ackerman, Ella Rabinovich, Eitan Farchi, Ateret Anaby Tavor


Abstract
We evaluate the robustness of several large language models on multiple datasets. Robustness here refers to the relative insensitivity of the model’s answers to meaning-preserving variants of their input. Benchmark datasets are constructed by introducing naturally-occurring, non-malicious perturbations, or by generating semantically equivalent paraphrases of input questions or statements. We further propose a novel metric for assessing a model robustness, and demonstrate its benefits in the non-adversarial scenario by empirical evaluation of several models on the created datasets.
Anthology ID:
2024.findings-emnlp.158
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2794–2802
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.158
DOI:
Bibkey:
Cite (ACL):
Samuel Ackerman, Ella Rabinovich, Eitan Farchi, and Ateret Anaby Tavor. 2024. A Novel Metric for Measuring the Robustness of Large Language Models in Non-adversarial Scenarios. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 2794–2802, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
A Novel Metric for Measuring the Robustness of Large Language Models in Non-adversarial Scenarios (Ackerman et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.158.pdf