@inproceedings{chen-etal-2026-distilling,
    title = "Distilling the Essence: Efficient Reasoning Distillation via Sequence Truncation",
    author = "Chen, Wei-Rui  and
      Kothapalli, Vignesh  and
      Fatahibaarzi, Ata  and
      Sang, Hejian  and
      Tang, Shao  and
      Song, Qingquan  and
      Wang, Zhipeng  and
      Abdul-Mageed, Muhammad",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.587/",
    pages = "12092--12122",
    ISBN = "979-8-89176-395-1",
    abstract = "Distilling the capabilities from a large reasoning model (LRM) to a smaller student model often involves training on substantial amounts of reasoning data. However, knowledge distillation (KD) over lengthy sequences with prompt (P), chain-of-thought (CoT), and answer (A) sections makes the process computationally expensive. In this work, we investigate how the allocation of supervision across different sections (P, CoT, A) affects student performance. Our analysis shows that selective KD over only the CoT tokens can be effective when the prompt and answer information is encompassed by it. Building on this insight, we establish a truncation protocol to quantify computation-quality tradeoffs as a function of sequence length. We observe that beyond a specific length, longer training sequences provide marginal returns for downstream performance but require substantially higher memory and FLOPs. To this end, training on only the first 50{\%} of tokens of every training sequence can retain, on average, {\ensuremath{\approx}}91{\%} of full-sequence performance on math benchmarks while reducing training time, memory usage, and FLOPs by about 50{\%} each. Codes are available at https://github.com/weiruichen01/distilling-the-essence."
}