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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Hao, Sun, Yizheng, Schlegel, Viktor, Yang, Kailai, Batista-Navarro, Riza, Nenadic, Goran
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918211013836800
author Li, Hao
Sun, Yizheng
Schlegel, Viktor
Yang, Kailai
Batista-Navarro, Riza
Nenadic, Goran
author_facet Li, Hao
Sun, Yizheng
Schlegel, Viktor
Yang, Kailai
Batista-Navarro, Riza
Nenadic, Goran
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_19081
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Arg-LLaDA: Argument Summarization via Large Language Diffusion Models and Sufficiency-Aware Refinement
Li, Hao
Sun, Yizheng
Schlegel, Viktor
Yang, Kailai
Batista-Navarro, Riza
Nenadic, Goran
Computation and Language
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.
title Arg-LLaDA: Argument Summarization via Large Language Diffusion Models and Sufficiency-Aware Refinement
topic Computation and Language
url https://arxiv.org/abs/2507.19081