@inproceedings{jain-etal-2025-first,
    title = "First-Step Advantage: Importance of Starting Right in Multi-Step Math Reasoning",
    author = "Jain, Kushal  and
      Miller, Moritz  and
      Tandon, Niket  and
      Shridhar, Kumar",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.findings-acl.42/",
    pages = "766--778",
    ISBN = "979-8-89176-256-5",
    abstract = "Language models can solve complex reasoning tasks better by learning to generate rationales for their predictions. Often these models know how to solve a task but their auto-regressive decoding nature leads to incorrect results if started incorrectly. We observe that smaller models in particular, when corrected, can solve a task that they would otherwise struggle with. We demonstrate this phenomenon by using a larger model to guide smaller models, which leads to significantly improved performance (up to +24 points on the GSM8K dataset by 7B models). To assist smaller models in initiating the starting step, we propose QuestCoT, where a smaller model first asks how to start before proceeding with a chain of reasoning. On various multistep mathematical reasoning datasets over multiple smaller models, we show that getting the start right can lead to significant performance gains across all models (gains of up to +6 points on GSM8K, +9 on SVAMP, +5 on ASDiv, and +7 on MultiArith)."
}