Disaster Question Answering with LoRA Efficiency and Accurate End Position

• URL: http://arxiv.org/abs/2602.21212v1
• Date: Wed, 28 Jan 2026 01:53:16 GMT
• Title: Disaster Question Answering with LoRA Efficiency and Accurate End Position
• Authors: Takato Yasuno,
• Abstract summary: This work introduces a disaster-focused question answering system based on Japanese disaster situations and response experiences.<n>We achieved 70.4% End Position accuracy with only 5.7% of the total parameters (6.7M/117M)<n>Future challenges include: establishing natural disaster Q&A benchmark datasets, fine-tuning foundation models with disaster knowledge, and developing lightweight and power-efficient edge AI Disaster Q&A applications.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Natural disasters such as earthquakes, torrential rainfall, floods, and volcanic eruptions occur with extremely low frequency and affect limited geographic areas. When individuals face disaster situations, they often experience confusion and lack the domain-specific knowledge and experience necessary to determine appropriate responses and actions. While disaster information is continuously updated, even when utilizing RAG search and large language models for inquiries, obtaining relevant domain knowledge about natural disasters and experiences similar to one's specific situation is not guaranteed. When hallucinations are included in disaster question answering, artificial misinformation may spread and exacerbate confusion. This work introduces a disaster-focused question answering system based on Japanese disaster situations and response experiences. Utilizing the cl-tohoku/bert-base-japanese-v3 + Bi-LSTM + Enhanced Position Heads architecture with LoRA efficiency optimization, we achieved 70.4\% End Position accuracy with only 5.7\% of the total parameters (6.7M/117M). Experimental results demonstrate that the combination of Japanese BERT-base optimization and Bi-LSTM contextual understanding achieves accuracy levels suitable for real disaster response scenarios, attaining a 0.885 Span F1 score. Future challenges include: establishing natural disaster Q\&A benchmark datasets, fine-tuning foundation models with disaster knowledge, developing lightweight and power-efficient edge AI Disaster Q\&A applications for situations with insufficient power and communication during disasters, and addressing disaster knowledge base updates and continual learning capabilities.

Related papers

• DisasterVQA: A Visual Question Answering Benchmark Dataset for Disaster Scenes [10.776782815521686]
  DisasterVQA consists of 1,395 real-world images and 4,405 expert-curated question-answer pairs spanning diverse events such as floods, wildfires, and earthquakes.<n>We benchmark seven state-of-the-art vision-language models and find performance variability across question types, disaster categories, regions, and humanitarian tasks.<n>DisasterVQA provides a challenging and practical benchmark to guide the development of more robust and operationally meaningful vision-language models for disaster response.
  arXiv  Detail & Related papers  (2026-01-20T10:50:46Z)
• MONITRS: Multimodal Observations of Natural Incidents Through Remote Sensing [39.47126465689941]
  We present MONITRS, a novel dataset of more than 10,000 FEMA disaster events with temporal satellite imagery and natural language annotations from news articles.<n>We demonstrate that fine-tuning existing MLLMs on our dataset yields significant performance improvements for disaster monitoring tasks.
  arXiv  Detail & Related papers  (2025-07-22T04:59:09Z)
• A Deep Learning framework for building damage assessment using VHR SAR and geospatial data: demonstration on the 2023 Turkiye Earthquake [1.6070833439280312]
  Building damage identification shortly after a disaster is crucial for guiding emergency response and recovery efforts.<n>We introduce a novel multimodal deep learning (DL) framework for detecting building damage using single-date very high resolution (VHR) Synthetic Aperture Radar (SAR) imagery.<n>Our method integrates SAR image patches, OpenStreetMap (OSM) building footprints, digital surface model (DSM) data, and structural and exposure attributes from the Global Earthquake Model (GEM)<n>Results highlight that incorporating geospatial features significantly enhances detection performance and generalizability to previously unseen areas.
  arXiv  Detail & Related papers  (2025-06-27T15:49:58Z)
• Harnessing Large Language Models for Disaster Management: A Survey [63.69308255115172]
  Large language models (LLMs) have revolutionized scientific research with their exceptional capabilities and transformed various fields.<n>This study aims to guide the professional community in developing advanced LLMs for disaster management to enhance the resilience against natural disasters.
  arXiv  Detail & Related papers  (2025-01-12T21:00:50Z)
• BRIGHT: A globally distributed multimodal building damage assessment dataset with very-high-resolution for all-weather disaster response [50.76124284445902]
  Building damage assessment (BDA) is an essential capability in the aftermath of a disaster to reduce human casualties.<n>Recent research focuses on the development of AI models to achieve accurate mapping of unseen disaster events.<n>We present a BDA dataset using veRy-hIGH-resoluTion optical and SAR imagery (BRIGHT) to support AI-based all-weather disaster response.
  arXiv  Detail & Related papers  (2025-01-10T14:57:18Z)
• CrisisSense-LLM: Instruction Fine-Tuned Large Language Model for Multi-label Social Media Text Classification in Disaster Informatics [50.122541222825156]
  This study introduces a novel approach to disaster text classification by enhancing a pre-trained Large Language Model (LLM)<n>Our methodology involves creating a comprehensive instruction dataset from disaster-related tweets, which is then used to fine-tune an open-source LLM.<n>This fine-tuned model can classify multiple aspects of disaster-related information simultaneously, such as the type of event, informativeness, and involvement of human aid.
  arXiv  Detail & Related papers  (2024-06-16T23:01:10Z)
• CrisisMatch: Semi-Supervised Few-Shot Learning for Fine-Grained Disaster Tweet Classification [51.58605842457186]
  We present a fine-grained disaster tweet classification model under the semi-supervised, few-shot learning setting. Our model, CrisisMatch, effectively classifies tweets into fine-grained classes of interest using few labeled data and large amounts of unlabeled data.
  arXiv  Detail & Related papers  (2023-10-23T07:01:09Z)
• Disaster Anomaly Detector via Deeper FCDDs for Explainable Initial Responses [0.0]
  In any disaster event, an initial response is the key to rescue within 72 hours and prompt recovery. Among machine learning algorithms, deep anomaly detection is effective in detecting devastation features that are different from everyday features. In this paper, we propose an anomaly detection application utilizing deeper fully convolutional data descriptions (FCDDs) We find that the deeper FCDD with a VGG16 backbone consistently outperformed other baselines CNN27, ResNet101, and Inceptionv3.
  arXiv  Detail & Related papers  (2023-06-05T00:44:39Z)
• Assessing out-of-domain generalization for robust building damage detection [78.6363825307044]
  Building damage detection can be automated by applying computer vision techniques to satellite imagery. Models must be robust to a shift in distribution between disaster imagery available for training and the images of the new event. We argue that future work should focus on the OOD regime instead.
  arXiv  Detail & Related papers  (2020-11-20T10:30:43Z)
• Physics-informed GANs for Coastal Flood Visualization [65.54626149826066]
  We create a deep learning pipeline that generates visual satellite images of current and future coastal flooding. By evaluating the imagery relative to physics-based flood maps, we find that our proposed framework outperforms baseline models in both physical-consistency and photorealism. While this work focused on the visualization of coastal floods, we envision the creation of a global visualization of how climate change will shape our earth.
  arXiv  Detail & Related papers  (2020-10-16T02:15:34Z)
• Social Media Information Sharing for Natural Disaster Response [0.0]
  Social media has become an essential channel for posting disaster-related information, which provide governments and relief agencies real-time data for better disaster management. This paper aims to improve disaster relief efficiency via mining and analyzing social media data like public attitudes towards disaster response and public demands for targeted relief supplies during different types of disasters.
  arXiv  Detail & Related papers  (2020-05-08T21:11:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.