EMNLP 2024finding1 citations

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.

BibTeX
@inproceedings{ackerman-etal-2024-novel,
    title = "A Novel Metric for Measuring the Robustness of Large Language Models in Non-adversarial Scenarios",
    author = "Ackerman, Samuel  and
      Rabinovich, Ella  and
      Farchi, Eitan  and
      Anaby Tavor, Ateret",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.findings-emnlp.158/",
    doi = "10.18653/v1/2024.findings-emnlp.158",
    pages = "2794--2802"
}