DMRetriever: A Family of Models for Improved Text Retrieval in Disaster Management
Abstract
DMRetriever, a series of dense retrieval models tailored for disaster management, achieves state-of-the-art performance across various search intents using a novel training framework and parameter-efficient design.
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
Models citing this paper 13
Browse 13 models citing this paperDatasets citing this paper 2
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper