@inproceedings{adatest,
    title = "Adaptive Testing and Debugging of {NLP} Models",
    author = "Ribeiro, Marco Tulio  and
      Lundberg, Scott",
    booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = may,
    year = "2022",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.acl-long.230",
    doi = "10.18653/v1/2022.acl-long.230",
    pages = "3253--3267",
    abstract = "Current approaches to testing and debugging NLP models rely on highly variable human creativity and extensive labor, or only work for a very restrictive class of bugs. We present AdaTest, a process which uses large scale language models (LMs) in partnership with human feedback to automatically write unit tests highlighting bugs in a target model. Such bugs are then addressed through an iterative text-fix-retest loop, inspired by traditional software development. In experiments with expert and non-expert users and commercial / research models for 8 different tasks, AdaTest makes users 5-10x more effective at finding bugs than current approaches, and helps users effectively fix bugs without adding new bugs.",
}