@inproceedings{wu-etal-2024-reuse,
    title = "Reuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment",
    author = "Wu, Zhaofeng  and
      Balashankar, Ananth  and
      Kim, Yoon  and
      Eisenstein, Jacob  and
      Beirami, Ahmad",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.emnlp-main.79/",
    doi = "10.18653/v1/2024.emnlp-main.79",
    pages = "1332--1353",
    abstract = "Aligning language models (LMs) based on human-annotated preference data is a crucial step in obtaining practical and performant LM-based systems. However, multilingual human preference data are difficult to obtain at scale, making it challenging to extend this framework to diverse languages. In this work, we evaluate a simple approach for zero-shot cross-lingual alignment, where a reward model is trained on preference data in one source language and directly applied to other target languages. On summarization and open-ended dialog generation, we show that this method is consistently successful under comprehensive evaluation settings, including human evaluation: cross-lingually aligned models are preferred by humans over unaligned models on up to {\ensuremath{>}}70{\%} of evaluation instances. We moreover find that a different-language reward model sometimes yields better aligned models than a same-language reward model. We also identify best practices when there is no language-specific data for even supervised finetuning, another component in alignment."
}