@inproceedings{li-etal-2025-warmup,
    title = "Warmup Generations: A Task-Agnostic Approach for Guiding Sequence-to-Sequence Learning with Unsupervised Initial State Generation",
    author = "Li, Senyu  and
      Sun, Zipeng  and
      Wang, Jiayi  and
      Liu, Xue  and
      Stenetorp, Pontus  and
      Reddy, Siva  and
      Adelani, David Ifeoluwa",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.434/",
    pages = "8870--8880",
    ISBN = "979-8-89176-251-0",
    abstract = "Traditional supervised fine-tuning (SFT) strategies for sequence-to-sequence tasks often train models to directly generate the target output. Recent work has shown that guiding models with intermediate steps{---}such as keywords, outlines, or reasoning chains{---}can significantly improve performance, coherence, and interpretability. However, these methods often depend on predefined intermediate formats and annotated data, limiting their scalability and generalizability. In this work, we introduce a task-agnostic framework that enables models to generate intermediate ``warmup'' sequences. These warmup sequences, serving as an initial state for subsequent generation, are optimized to enhance the probability of generating the target sequence without relying on external supervision or human-designed structures. Drawing inspiration from reinforcement learning principles, our method iteratively refines these intermediate steps to maximize their contribution to the final output, similar to reward-driven optimization in reinforcement learning with human feedback. Experimental results across tasks such as translation, summarization, and multi-choice question answering for logical reasoning show that our approach outperforms traditional SFT methods, and offers a scalable and flexible solution for sequence-to-sequence tasks."
}