@inproceedings{yuan-etal-2025-following,
    title = "Following Length Constraints in Instructions",
    author = "Yuan, Weizhe  and
      Kulikov, Ilia  and
      Yu, Ping  and
      Cho, Kyunghyun  and
      Sukhbaatar, Sainbayar  and
      Weston, Jason E  and
      Xu, Jing",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.1233/",
    pages = "24243--24254",
    ISBN = "979-8-89176-332-6",
    abstract = "Aligned instruction following models can better fulfill user requests than their unaligned counterparts. However, it has been shown that there is a length bias in evaluation of such models, and that training algorithms tend to exploit this bias by learning longer responses. In this work we show how to train models that can be controlled at inference time with instructions containing desired length constraints. Such models are superior in length instructed evaluations, outperforming standard instruction following models such as GPT4, Llama 3 and Mixtral."
}