A Dynamic Fusion Model for Consistent Crisis Response
This addresses the need for consistent communication to build trust with crisis-affected populations, representing an incremental improvement in a specific domain.
The paper tackled the problem of maintaining stylistic consistency in automated crisis response generation, proposing a novel metric and fusion-based method that outperformed baselines in both response quality and stylistic uniformity across multiple datasets.
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.