chatClimate：让对话式人工智能扎根于气候科学
chatClimate: Grounding Conversational AI in Climate Science
AI总结：
针对大语言模型存在幻觉、信息过时的问题，研究融合IPCC AR6的信息增强GPT-4，推出对话式AI原型chatClimate，经IPCC作者评估，混合模式的chatClimate答案准确性更高，可推广至特定领域聊天机器人。
摘要：
大语言模型（Large Language Models, LLMs）近年来取得了显著进展，在问答任务（question-answering, QA）中实现了出色的表现。但它们仍面临两大主要挑战：幻觉问题，以及训练阶段结束后信息过时的问题。在气候变化这类关键领域中，这些挑战尤为突出——在有限时间内从可靠来源获取准确、最新的信息至关重要，却也难度颇高。为突破这些障碍，一种可行的解决方案是让LLMs能够访问外部的、具备科学准确性与可靠性的信息源（即长期记忆），从而持续更新其知识，避免不准确、错误或过时信息的传播。本研究中，我们通过整合政府间气候变化专门委员会第六次评估报告（IPCC AR6）——该领域最全面、最新且最可靠的信息来源——的信息，对GPT-4进行了增强。我们推出了对话式AI原型chatClimate，可通过www.chatclimate.ai访问，并在三种不同的问答场景下验证了其准确回答高难度问题的能力，三种场景分别为：1）由GPT-4作答，2）由chatClimate作答，3）由混合模式chatClimate作答。我们的IPCC作者团队对答案及其来源进行了评估，他们利用自身专业知识对答案的准确性打分，分值范围为1（极低）到5（极高）。评估结果显示，混合模式的chatClimate能提供更准确的答案，凸显了我们所提方案的有效性。该方法可轻松扩展应用于特定领域的聊天机器人，从而实现可靠、准确的信息传递。
英文摘要：
Large Language Models (LLMs) have made significant progress in recent years, achieving remarkable results in question-answering tasks (QA). However, they still face two major challenges: hallucination and outdated information after the training phase. These challenges take center stage in critical domains like climate change, where obtaining accurate and up-to-date information from reliable sources in a limited time is essential and difficult. To overcome these barriers, one potential solution is to provide LLMs with access to external, scientifically accurate, and robust sources (long-term memory) to continuously update their knowledge and prevent the propagation of inaccurate, incorrect, or outdated information. In this study, we enhanced GPT-4 by integrating the information from the Sixth Assessment Report of the Intergovernmental (IPCC AR6), the most comprehensive, up-to-date, and reliable source in this domain. We present our conversational AI prototype, available at www.chatclimate.ai and demonstrate its ability to answer challenging questions accurately in three different QA scenarios: asking from 1) GPT-4, 2) chatClimate, and 3) hybrid chatClimate. The answers and their sources were evaluated by our team of IPCC authors, who used their expert knowledge to score the accuracy of the answers from 1 (very-low) to 5 (very-high). The evaluation showed that the hybrid chatClimate provided more accurate answers, highlighting the effectiveness of our solution. This approach can be easily scaled for chatbots in specific domains, enabling the delivery of reliable and accurate information.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
