# A Dynamic Fusion Model for Consistent Crisis Response

arXiv: https://arxiv.org/abs/2509.01053 · HTML: https://mlsanity.com/paper/2509.01053/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 65 references that are in the map.
- First posted on arXiv 1 Sep 2025.

## Builds on (most cited first, 18 of 18)

- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [ProSA: Assessing and Understanding the Prompt Sensitivity of LLMs](https://mlsanity.com/paper/2410.12405/) (2024)
- [Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models](https://mlsanity.com/paper/2402.13064/) (2024)
- [Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrievers](https://mlsanity.com/paper/2404.07220/) (2024)
- [Generate, Prune, Select: A Pipeline for Counterspeech Generation against Online Hate Speech](https://mlsanity.com/paper/2106.01625/) (2021)
- [HumAID: Human-Annotated Disaster Incidents Data from Twitter with Deep Learning Benchmarks](https://mlsanity.com/paper/2104.03090/) (2021)
- [DisasterResponseGPT: Large Language Models for Accelerated Plan of Action Development in Disaster Response Scenarios](https://mlsanity.com/paper/2306.17271/) (2023)
- [CrisisSense-LLM: Instruction Fine-Tuned Large Language Model for Multi-label Social Media Text Classification in Disaster Informatics](https://mlsanity.com/paper/2406.15477/) (2024)
- [LLM-Assisted Crisis Management: Building Advanced LLM Platforms for Effective Emergency Response and Public Collaboration](https://mlsanity.com/paper/2402.10908/) (2024)
- [Harnessing Large Language Models for Disaster Management: A Survey](https://mlsanity.com/paper/2501.06932/) (2025)
- [Balancing Enhancement, Harmlessness, and General Capabilities: Enhancing Conversational LLMs with Direct RLHF](https://mlsanity.com/paper/2403.02513/) (2024)
- [Outcome-Constrained Large Language Models for Countering Hate Speech](https://mlsanity.com/paper/2403.17146/) (2024)
- [Prompt Sentiment: The Catalyst for LLM Change](https://mlsanity.com/paper/2503.13510/) (2025)
- [DisasterQA: A Benchmark for Assessing the performance of LLMs in Disaster Response](https://mlsanity.com/paper/2410.20707/) (2024)
- [Consistency of Responses and Continuations Generated by Large Language Models on Social Media](https://mlsanity.com/paper/2501.08102/) (2025)
- [Echoes of Discord: Forecasting Hater Reactions to Counterspeech](https://mlsanity.com/paper/2501.16235/) (2025)
- [Infrastructure Ombudsman: Mining Future Failure Concerns from Structural Disaster Response](https://mlsanity.com/paper/2402.13528/) (2024)
- [Detecting Actionable Requests and Offers on Social Media During Crises Using LLMs](https://mlsanity.com/paper/2504.16144/) (2025)

## Abstract (arXiv)

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.