@inproceedings{arad-etal-2024-refact,
    title = "{R}e{FACT}: Updating Text-to-Image Models by Editing the Text Encoder",
    author = "Arad, Dana  and
      Orgad, Hadas  and
      Belinkov, Yonatan",
    editor = "Duh, Kevin  and
      Gomez, Helena  and
      Bethard, Steven",
    booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2024.naacl-long.140/",
    doi = "10.18653/v1/2024.naacl-long.140",
    pages = "2537--2558",
    abstract = "Our world is marked by unprecedented technological, global, and socio-political transformations, posing a significant challenge to textto-image generative models. These models encode factual associations within their parameters that can quickly become outdated, diminishing their utility for end-users. To that end, we introduce ReFACT, a novel approach for editing factual associations in text-to-image models without relaying on explicit input from end-users or costly re-training. ReFACT updates the weights of a specific layer in the text encoder, modifying only a tiny portion of the model`s parameters and leaving the rest of the model unaffected.We empirically evaluate ReFACT on an existing benchmark, alongside a newly curated dataset.Compared to other methods, ReFACT achieves superior performance in both generalization to related concepts and preservation of unrelated concepts.Furthermore, ReFACT maintains image generation quality, making it a practical tool for updating and correcting factual information in text-to-image models."
}