Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

HiFlow: Hierarchical Feedback-Driven Optimization for Constrained Long-Form Text Generation

Yifan Zhu, Guanting Chen, Bing Wei, Haoran Luo

TL;DR

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.

Abstract

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.

HiFlow: Hierarchical Feedback-Driven Optimization for Constrained Long-Form Text Generation

TL;DR

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.

Abstract

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.
Paper Structure (37 sections, 37 equations, 15 figures, 1 table, 1 algorithm)

This paper contains 37 sections, 37 equations, 15 figures, 1 table, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Preliminaries
  4. Methodology: HiFlow
  5. Constraint-Aware Hierarchical Plan Modeling
  6. Binary Relevance Filtering
  7. Reward-Guided Optimization
  8. Main Workflow
  9. Experiments
  10. Experimental Setup
  11. Main Results (RQ1)
  12. Ablation Study on the Effectiveness of HiFlow’s Key Components (RQ2)
  13. Constraint-Aware Workflow Design (RQ3)
  14. Adaptive Workflow Optimization (RQ4)
  15. Feedback-Coupled Coordination (RQ5)
  16. ...and 22 more sections

Figures (15)

  • Figure 1: An example of constrained long-form text generation in HiFlow, coordinating planning, generation, and feedback.
  • Figure 2: Framework comparison of HiFlow, LongWriter, and CogWriter, highlighting key differences in planning, reviewing, and generation for producing coherent, high-quality long-form text.
  • Figure 3: Overview of the HiFlow framework: a constrained generation process guided by reward signals, ensuring high-quality outputs, task-specific coherence, and structural consistency.
  • Figure 4: Results across backbone models. (a) Text quality evaluation. (b) Constraint-following accuracy. (c) Ablation study on constraint components. (d–e) Constraint accuracy and text quality on Qwen2.5-7B-Instruct. (f–g) Constraint accuracy and text quality on LLaMA3.
  • Figure 5: Comprehensive analysis of HiFlow. (a) Case study illustrating generation quality under a representative constraint prompt. (b) Multi-dimensional performance comparison. (c) Accuracy evolution across evaluation stages. (d) Efficiency–accuracy trade-off.
  • ...and 10 more figures

Theorems & Definitions (6)

  • proof
  • proof
  • proof
  • proof
  • proof
  • proof