用AI自动追踪气候预警系统投资，提升透明度与准确性。
AI for Climate Finance: Agentic Retrieval and Multi-Step Reasoning for Early Warning System Investments
- 构建基于检索增强生成的智能代理系统，实现多步推理
- 在真实项目文档中达87%准确率，优于其他方法
- 适合关注气候金融透明与AI应用的研究者
追踪气候适应性投资是一项复杂且依赖专业知识的任务，尤其针对早期预警系统（EWS），其在多边开发银行（MDBs）和基金间缺乏标准化财务报告。为应对这一挑战，我们提出一种基于大语言模型的智能代理系统，整合上下文检索、微调与多步推理，用于提取相关财务数据、分类投资并确保符合资助指南。研究聚焦于气候风险与早期预警系统（CREWS）基金的实际应用，分析25份MDB项目文件，评估多种AI分类方法：零样本、少样本学习、微调的Transformer分类器、思维链（CoT）提示，以及基于代理的检索增强生成（RAG）方法。结果表明，代理式RAG方法显著优于其他方法，准确率达87%，精确率为89%，召回率为83%。此外，我们还贡献了一个基准数据集和专家标注语料库，为未来人工智能驱动的金融追踪与气候金融透明性研究提供宝贵资源。
原文摘要 · Abstract (English)
Tracking financial investments in climate adaptation is a complex and expertise-intensive task, particularly for Early Warning Systems (EWS), which lack standardized financial reporting across multilateral development banks (MDBs) and funds. To address this challenge, we introduce an LLM-based agentic AI system that integrates contextual retrieval, fine-tuning, and multi-step reasoning to extract relevant financial data, classify investments, and ensure compliance with funding guidelines. Our study focuses on a real-world application: tracking EWS investments in the Climate Risk and Early Warning Systems (CREWS) Fund. We analyze 25 MDB project documents and evaluate multiple AI-driven classification methods, including zero-shot and few-shot learning, fine-tuned transformer-based classifiers, chain-of-thought (CoT) prompting, and an agent-based retrieval-augmented generation (RAG) approach. Our results show that the agent-based RAG approach significantly outperforms other methods, achieving 87\% accuracy, 89\% precision, and 83\% recall. Additionally, we contribute a benchmark dataset and expert-annotated corpus, providing a valuable resource for future research in AI-driven financial tracking and climate finance transparency.
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。