提升灾难响应中语言模型回复的风格一致性，增强受灾人群信任。
A Dynamic Fusion Model for Consistent Crisis Response
- 基于新提出的风格一致性度量，分两阶段融合优化生成回复
- 在多个数据集上显著降低回复风格差异，同时保持高质量输出
- 适合需要稳定沟通形象的应急响应、人道援助等场景
为应对灾情中高效沟通的迫切需求，基于语言模型的自动化响应被提出以辅助危机沟通。一个关键却常被忽视的因素是回复风格的一致性，这可能影响受灾人群对回应者的信任。尽管重要，但极少研究关注如何维持生成回复间的风格一致性。为此，我们提出一种新的风格一致性评估指标，并引入基于该指标的融合生成方法。该方法采用两阶段流程：首先评估候选回复的风格，再通过实例级融合优化并整合回复。此过程在保证生成质量的同时，显著减少不同实例间风格差异。跨多个数据集的实验结果表明，本方法在回复质量与风格统一性方面均持续优于基线模型。
原文摘要 · Abstract (English)
In response to the urgent need for effective communication with crisis-affected populations, automated responses driven by language models have been proposed to assist in crisis communications. A critical yet often overlooked factor is the consistency of response style, which could affect the trust of affected individuals in responders. Despite its importance, few studies have explored methods for maintaining stylistic consistency across generated responses. To address this gap, we propose a novel metric for evaluating style consistency and introduce a fusion-based generation approach grounded in this metric. Our method employs a two-stage process: it first assesses the style of candidate responses and then optimizes and integrates them at the instance level through a fusion process. This enables the generation of high-quality responses while significantly reducing stylistic variation between instances. Experimental results across multiple datasets demonstrate that our approach consistently outperforms baselines in both response quality and stylistic uniformity.
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。