@inproceedings{stefanik-2022-methods,
    title = "Methods for Estimating and Improving Robustness of Language Models",
    author = "Stefanik, Michal",
    editor = "Ippolito, Daphne  and
      Li, Liunian Harold  and
      Pacheco, Maria Leonor  and
      Chen, Danqi  and
      Xue, Nianwen",
    booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Student Research Workshop",
    month = jul,
    year = "2022",
    address = "Hybrid: Seattle, Washington + Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2022.naacl-srw.6/",
    doi = "10.18653/v1/2022.naacl-srw.6",
    pages = "44--51",
    abstract = "Despite their outstanding performance, large language models (LLMs) suffer notorious flaws related to their preference for shallow textual relations over full semantic complexity of the problem. This proposal investigates a common denominator of this problem in their weak ability to generalise outside of the training domain. We survey diverse research directions providing estimations of model generalisation ability and find that incorporating some of these measures in the training objectives leads to enhanced distributional robustness of neural models. Based on these findings, we present future research directions enhancing the robustness of LLMs."
}