ACL Findings2026
BoundRL: Efficient Token-level Structured Text Segmentation through Reinforced Boundary Generation
Haoyuan Li, Zhengyuan Shen, Sullam Jeoung, Yueyan Chen, Jiayu Li, Qi Zhu, Shuai Wang, Vassilis N. Ioannidis, Huzefa Rangwala
Abstract
Structured texts refer to texts containing structured elements beyond plain texts, such as code snippets and placeholders. Such structured texts increasingly require segmentation into semantically meaningful components, which cannot be effectively handled by conventional sentence-level segmentation methods. To address this, we propose BoundRL, a novel approach that jointly performs efficient tokenlevel 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 output tokens 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.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on7
- Semantic Self-Segmentation for Abstractive Summarization of Long Documents in Low-Resource RegimesGianluca Moro, Luca RagazziAAAI 2022 · 67 citations
- A Joint Model for Document Segmentation and Segment LabelingJoe Barrow, Rajiv Jain, Vlad I. Morariu, Varun Manjunatha et al.ACL 2020 · 47 citations
- RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy OptimizationYihong Dong, Xue Jiang, Yongding Tao, Huanyu Liu et al.ACL 2026 · 34 citations
- LumberChunker: Long-Form Narrative Document SegmentationAndré V. Duarte, João D. S. Marques, Miguel Graça, Miguel Freire et al.EMNLP Findings 2024 · 27 citations
- Symbolic Prompt Program Search: A Structure-Aware Approach to Efficient Compile-Time Prompt OptimizationTobias Schnabel, Jennifer NevilleEMNLP Findings 2024 · 7 citations
Related papers
- LENS: Learning to Segment Anything with Unified Reinforced ReasoningLianghui Zhu, Bin Ouyang, Yuxuan Zhang, Tianheng Cheng et al.AAAI 2026 · 7 citations
- Crossing the Reward Bridge: Expanding Reinforcement Learning with Verifiable Rewards Across Diverse DomainsYi Su, Dian Yu, Linfeng Song, Juntao Li et al.ACL 2026
- CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement LearningLong Xing, Xiaoyi Dong, Yuhang Zang, Yuhang Cao et al.ICLR 2026 · 37 citations
- Training Diffusion Language Models for Black-Box OptimizationZipeng Sun, Can Chen, Ye Yuan, Haolun Wu et al.ICML 2026
- TLDR: Token-Level Detective Reward Model for Large Vision Language ModelsDeqing Fu, Tong Xiao, Rui Wang, Wang Zhu et al.ICLR 2025
