Summaries of real-world events can become outdated as contexts evolve and new information arrives. A common response is to generate a new summary from the updated context, but full regeneration discards the previous draft, can obscure what changed, and may be unnecessary when only a few claims are unsupported. We study localized faithfulness repair: updating outdated spans in an existing summary while preserving supported content. We propose DETECT-REMASK-REPAIR, a diffusion-based framework that identifies, remasks, and repairs outdated regions with masked diffusion language models. To evaluate evolving-context summarization, we introduce StreamSum, a benchmark of synthetic event timelines. Experiments on DialogSum and StreamSum show that localized diffusion repair provides a controllable alternative to full rewriting: faithfulness-steered repair improves early drafts, one-step repair reduces repair cost to under half a second, with the framework enabling faithfulness-speed-preservation tradeoffs across datasets. We also find that the framework can provide a post-hoc correction step that improves faithfulness for autoregressive systems.

翻译：现实世界事件的摘要可能因上下文演变和新信息抵达而过时。常见做法是根据更新后的上下文生成新摘要，但完全重新生成会丢弃先前草稿、掩盖变化内容，且当仅有少量陈述缺乏依据时可能不必要。我们研究局部忠实性修复：在保留已有摘要中受支持内容的同时，更新过时片段。我们提出检测-重掩-修复（DETECT-REMASK-REPAIR）框架，该框架基于扩散模型，通过掩码扩散语言模型识别、重掩并修复过时区域。为评估动态上下文摘要任务，我们引入StreamSum基准数据集——包含合成事件时间线。在DialogSum和StreamSum上的实验表明，局部扩散修复提供了一种可替代完全重写的可控方案：忠实性导向修复可改进初始草稿，单步修复可将修复成本降至半秒内，且该框架支持跨数据集的忠实性-速度-内容保留权衡。我们还发现该框架可作为事后修正步骤，提升自回归系统的忠实性。