通过分层反馈优化，提升长文本生成的结构一致性与约束满足度。
HiFlow: Hierarchical Feedback-Driven Optimization for Constrained Long-Form Text Generation
- 分两层优化：先规划全局结构，再生成具体内容。
- 闭环反馈机制使生成结果逐步逼近约束条件。
- 适合需要严谨结构的长文生成任务，如报告、论文写作。
大语言模型在短文本生成中表现良好，但在复杂约束下的长文本生成仍面临挑战。这类任务涉及全局结构一致性、局部语义连贯性及约束可行性等多重紧密耦合目标，构成复杂的约束优化问题。现有方法多依赖静态规划或离线监督，难以在生成过程中有效协调全局与局部目标。为此，我们提出HiFlow，一种面向约束型长文本生成的分层反馈优化框架。该框架将生成过程建模为两级优化：规划层负责全局结构与约束建模，生成层实现条件化文本生成。通过引入约束感知的计划筛选与双层闭环反馈，HiFlow实现了规划质量与生成行为的联合优化，逐步引导模型生成高质量且满足约束的输出。在多个基线模型上的实验验证了其有效性。
原文摘要 · Abstract (English)
Large language models perform well in short text generation but still struggle with long text generation, particularly under complex constraints. Such tasks involve multiple tightly coupled objectives, including global structural consistency, local semantic coherence, and constraint feasibility, forming a challenging constrained optimization problem. Existing approaches mainly rely on static planning or offline supervision, limiting effective coordination between global and local objectives during generation. To address these challenges, we propose HiFlow, a hierarchical feedback-driven optimization framework for constrained long text generation. HiFlow formulates generation as a two-level optimization process, consisting of a planning layer for global structure and constraint modeling, and a generation layer for conditioned text generation. By incorporating constraint-aware plan screening and closed-loop feedback at both levels, HiFlow enables joint optimization of planning quality and generation behavior, progressively guiding the model toward high-quality, constraint-satisfying outputs. Experiments on multiple backbones confirm HiFlow's effectiveness over baseline methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。