Arg-LLaDA: Argument Summarization via Large Language Diffusion Models and Sufficiency-Aware Refinement
This work addresses the underexplored generation stage in argument summarization for debates, offering an incremental improvement over existing methods.
The paper tackled the problem of generating concise, structured summaries for complex debates by addressing limitations in single-pass generation methods, and the result was that Arg-LLaDA outperformed state-of-the-art baselines in 7 out of 10 automatic metrics and showed substantial improvements in human evaluations for coverage, faithfulness, and conciseness.
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.