Arg-LLaDA: Argument Summarization via Large Language Diffusion Models and Sufficiency-Aware Refinement

TL;DR

Arg-LLaDA introduces an iterative, sufficiency-aware diffusion framework for argument summarization, significantly improving the faithfulness, coherence, and conciseness of generated summaries over existing methods.

Contribution

We propose Arg-LLaDA, a novel diffusion-based model that iteratively refines argument summaries using sufficiency-guided remasking and regeneration, addressing limitations of single-pass generation.

Findings

Outperforms state-of-the-art baselines on 7 out of 10 metrics.

Human evaluations show improved coverage, faithfulness, and conciseness.

Demonstrates effective iterative refinement in argument summarization.

Abstract

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.