A Dynamic Fusion Model for Consistent Crisis Response

Xiaoying Song, Anirban Saha Anik, Eduardo Blanco, Vanessa Frias-Martinez, Lingzi Hong


Abstract
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.
Anthology ID:
2025.findings-emnlp.149
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2753–2768
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.149/
DOI:
Bibkey:
Cite (ACL):
Xiaoying Song, Anirban Saha Anik, Eduardo Blanco, Vanessa Frias-Martinez, and Lingzi Hong. 2025. A Dynamic Fusion Model for Consistent Crisis Response. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 2753–2768, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
A Dynamic Fusion Model for Consistent Crisis Response (Song et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.149.pdf
Checklist:
 2025.findings-emnlp.149.checklist.pdf