@inproceedings{li-etal-2026-boundrl,
    title = "{B}ound{RL}: Efficient Token-level Structured Text Segmentation through Reinforced Boundary Generation",
    author = "Li, Haoyuan  and
      Shen, Zhengyuan  and
      Jeoung, Sullam  and
      Chen, Yueyan  and
      Li, Jiayu  and
      Zhu, Qi  and
      Wang, Shuai  and
      Ioannidis, Vassilis N.  and
      Rangwala, Huzefa",
    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.1733/",
    pages = "34706--34726",
    ISBN = "979-8-89176-395-1",
    abstract = "Structured texts {--} from technical reports to AI prompts {--} increasingly require segmentation into semantically meaningful components. Such texts often contain elements beyond plain language, such as code snippets, which conventional sentence-level segmentation methods cannot handle effectively. To address this, we propose BoundRL, a novel approach that jointly performs efficient token-level text segmentation and label prediction for long structured texts. Instead of generating full texts for each segment, it generates only starting tokens and reconstructs the complete texts by locating these tokens within the original texts, thereby reducing inference costs by 90{\%} and minimizing hallucination. To train the models for the boundary generation, BoundRL performs reinforcement learning with verifiable rewards (RLVR) that jointly optimizes document reconstruction fidelity and semantic alignment. It further mitigates entropy collapse by constructing intermediate candidates by perturbing segment boundaries and labels to create stepping stones toward higher-quality solutions. Experiments show that BoundRL enables small language models (1.7B parameters) to outperform few-shot prompting with much larger models as well as SFT and standard RLVR baselines on complex prompts used for LLM applications."
}