用大模型精准识别灾难中求助与援助信息并排序优先级
Detecting Actionable Requests and Offers on Social Media During Crises Using LLMs
- 构建三级分类体系，细化灾情信息为物资、人员、行动三类
- 通过检索特定样本提升模型对求助/援助的识别准确率
- 评估信息可操作性，帮助救援机构快速响应紧急需求
自然灾害常引发社交媒体上大量信息，包括求助、援助、情绪表达和一般更新。为提升人道组织响应效率，我们提出一个细粒度的层级分类体系，将危机相关信息按物资、应急人员和行动三个维度系统分类。利用大语言模型（LLMs）能力，引入查询特定少样本学习（QSF Learning），从嵌入数据库中检索类别相关标注样本，增强模型在检测与分类中的表现。除分类外，还评估信息的可操作性，以优先处理需立即响应的内容。大量实验表明，该方法优于基线提示策略，能有效识别并优先处理可执行的求助与援助信息。
原文摘要 · Abstract (English)
Natural disasters often result in a surge of social media activity, including requests for assistance, offers of help, sentiments, and general updates. To enable humanitarian organizations to respond more efficiently, we propose a fine-grained hierarchical taxonomy to systematically organize crisis-related information about requests and offers into three critical dimensions: supplies, emergency personnel, and actions. Leveraging the capabilities of Large Language Models (LLMs), we introduce Query-Specific Few-shot Learning (QSF Learning) that retrieves class-specific labeled examples from an embedding database to enhance the model's performance in detecting and classifying posts. Beyond classification, we assess the actionability of messages to prioritize posts requiring immediate attention. Extensive experiments demonstrate that our approach outperforms baseline prompting strategies, effectively identifying and prioritizing actionable requests and offers.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。