The recent advancement of large language models (LLMs) represents a transformational capability at the frontier of artificial intelligence (AI) and machine learning (ML). However, LLMs are generalized models, trained on extensive text corpus, and often struggle to provide context-specific information, particularly in areas requiring specialized knowledge such as wildfire details within the broader context of climate change. For decision-makers and policymakers focused on wildfire resilience and adaptation, it is crucial to obtain responses that are not only precise but also domain-specific, rather than generic. To that end, we developed WildfireGPT, a prototype LLM agent designed to transform user queries into actionable insights on wildfire risks. We enrich WildfireGPT by providing additional context such as climate projections and scientific literature to ensure its information is current, relevant, and scientifically accurate. This enables WildfireGPT to be an effective tool for delivering detailed, user-specific insights on wildfire risks to support a diverse set of end users, including researchers, engineers, urban planners, emergency managers, and infrastructure operators.

翻译：大语言模型（LLM）的最新进展代表了人工智能（AI）与机器学习（ML）前沿领域的变革性能力。然而，LLM作为基于海量文本语料训练的通用化模型，往往难以提供情境化信息，尤其在气候变化宏观背景下涉及野火细节等需要专业知识的领域。对于致力于野火韧性与适应能力的决策者与政策制定者而言，获取既精准又具备领域特异性（而非泛化性）的响应至关重要。为此，我们开发了WildfireGPT——一种旨在将用户查询转化为野火风险可操作洞见的原型LLM智能体。通过补充气候预测与科学文献等额外语境信息，我们强化了WildfireGPT，确保其输出信息的时效性、相关性与科学准确性。这使得WildfireGPT能够成为传递精细化、用户定制化野火风险洞见的有效工具，从而支撑包括研究者、工程师、城市规划者、应急管理人员及基础设施运营者在内的多元化终端用户群体。