@inproceedings{micheli-fleuret-2021-language,
    title = "Language Models are Few-Shot Butlers",
    author = "Micheli, Vincent  and
      Fleuret, Francois",
    editor = "Moens, Marie-Francine  and
      Huang, Xuanjing  and
      Specia, Lucia  and
      Yih, Scott Wen-tau",
    booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2021",
    address = "Online and Punta Cana, Dominican Republic",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2021.emnlp-main.734/",
    doi = "10.18653/v1/2021.emnlp-main.734",
    pages = "9312--9318",
    abstract = "Pretrained language models demonstrate strong performance in most NLP tasks when fine-tuned on small task-specific datasets. Hence, these autoregressive models constitute ideal agents to operate in text-based environments where language understanding and generative capabilities are essential. Nonetheless, collecting expert demonstrations in such environments is a time-consuming endeavour. We introduce a two-stage procedure to learn from a small set of demonstrations and further improve by interacting with an environment. We show that language models fine-tuned with only 1.2{\%} of the expert demonstrations and a simple reinforcement learning algorithm achieve a 51{\%} absolute improvement in success rate over existing methods in the ALFWorld environment."
}