@inproceedings{stefanik-etal-2023-soft,
    title = "Soft Alignment Objectives for Robust Adaptation of Language Generation",
    author = "{\v{S}}tef{\'a}nik, Michal  and
      Kadlcik, Marek  and
      Sojka, Petr",
    editor = "Rogers, Anna  and
      Boyd-Graber, Jordan  and
      Okazaki, Naoaki",
    booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2023.acl-long.492/",
    doi = "10.18653/v1/2023.acl-long.492",
    pages = "8837--8853",
    abstract = "Domain adaptation allows generative language models to address specific flaws caused by the domain shift of their application. However, the traditional adaptation by further training on in-domain data rapidly weakens the model{'}s ability to generalize to other domains, making the open-ended deployments of the adapted models prone to errors. This work introduces novel training objectives built upon a semantic similarity of the predicted tokens to the reference. Our results show that (1) avoiding the common assumption of a single correct prediction by constructing the training target from tokens' semantic similarity can largely mitigate catastrophic forgetting of adaptation, while (2) preserving the adaptation in-domain quality, (3) with negligible additions to compute costs. In the broader context, the objectives grounded in a continuous token similarity pioneer the exploration of the middle ground between the efficient but naive exact-match token-level objectives and expressive but computationally- and resource-intensive sequential objectives."
}