Paper ID: 2408.01963

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

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

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.

Submitted: Aug 4, 2024