用迭代修正提升论点摘要的准确性和完整性
Arg-LLaDA: Argument Summarization via Large Language Diffusion Models and Sufficiency-Aware Refinement
- 通过可调节掩码与充分性检查，逐轮优化摘要内容
- 在两个数据集上7项指标超越现有方法，人类评估更优
- 适合需要高可信度摘要的辩论分析场景
论点摘要旨在生成复杂多视角争论的简洁结构化表示。尽管近期研究在论点组件识别与聚类方面取得进展，生成阶段仍缺乏深入探索。现有方法通常采用单次生成，难以支持事实修正或结构优化。为此，我们提出Arg-LLaDA，一种基于大语言扩散模型的新型框架，通过充分性引导的重掩码与重生成机制，迭代改进摘要。该方法结合灵活的掩码控制器与充分性检查模块，识别并修正无支撑、冗余或不完整的段落，从而生成更忠实、简洁、连贯的输出。在两个基准数据集上的实证结果表明，Arg-LLaDA在10项自动评估指标中有7项优于当前最优基线。此外，人工评估显示其在覆盖度、忠实性、简洁性等核心维度均有显著提升，验证了迭代式、充分性感知生成策略的有效性。
原文摘要 · Abstract (English)
Argument summarization aims to generate concise, structured representations of complex, multi-perspective debates. While recent work has advanced the identification and clustering of argumentative components, the generation stage remains underexplored. Existing approaches typically rely on single-pass generation, offering limited support for factual correction or structural refinement. To address this gap, we introduce Arg-LLaDA, a novel large language diffusion framework that iteratively improves summaries via sufficiency-guided remasking and regeneration. Our method combines a flexible masking controller with a sufficiency-checking module to identify and revise unsupported, redundant, or incomplete spans, yielding more faithful, concise, and coherent outputs. Empirical results on two benchmark datasets demonstrate that Arg-LLaDA surpasses state-of-the-art baselines in 7 out of 10 automatic evaluation metrics. In addition, human evaluations reveal substantial improvements across core dimensions, coverage, faithfulness, and conciseness, validating the effectiveness of our iterative, sufficiency-aware generation strategy.
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。