DMRetriever: A Family of Models for Improved Text Retrieval in Disaster Management
This addresses the problem of inconsistent and unreliable information retrieval for disaster management professionals, though it is incremental as it adapts existing dense retrieval methods to a specific domain.
The paper tackles the lack of specialized retrieval models for disaster management by introducing DMRetriever, a family of dense retrieval models that achieve state-of-the-art performance across all six search intents at every model scale, with a 596M model outperforming baselines over 13.3 times larger.
Effective and efficient access to relevant information is essential for disaster management. However, no retrieval model is specialized for disaster management, and existing general-domain models fail to handle the varied search intents inherent to disaster management scenarios, resulting in inconsistent and unreliable performance. To this end, we introduce DMRetriever, the first series of dense retrieval models (33M to 7.6B) tailored for this domain. It is trained through a novel three-stage framework of bidirectional attention adaptation, unsupervised contrastive pre-training, and difficulty-aware progressive instruction fine-tuning, using high-quality data generated through an advanced data refinement pipeline. Comprehensive experiments demonstrate that DMRetriever achieves state-of-the-art (SOTA) performance across all six search intents at every model scale. Moreover, DMRetriever is highly parameter-efficient, with 596M model outperforming baselines over 13.3 X larger and 33M model exceeding baselines with only 7.6% of their parameters. All codes, data, and checkpoints are available at https://github.com/KaiYin97/DMRETRIEVER