arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2304.00116cs.CLcs.IR
收藏

利用气候资源增强大型语言模型

Enhancing Large Language Models with Climate Resources

FAU Erlangen-Nuremberg(埃尔朗根-纽伦堡大学);University of Oxford(牛津大学);University of Zurich(苏黎世大学);ETH Zurich(苏黎世联邦理工学院);Council on Economic Policies(经济政策委员会)

Mathias Kraus, Julia Anna Bingler, Markus Leippold, Tobias Schimanski, Chiara Colesanti Senni, Dominik Stammbach, Saeid Ashraf Vaghefi, Nicolas Webersinke

AI总结:

本研究将LLMs视为可访问多源数据库的智能体,通过集成ClimateWatch和Google搜索,克服了模型语言不精确和缺乏最新信息的局限,在气候变化领域提供了更可靠准确的信息。

摘要:

大型语言模型(LLMs)通过展现其在跨多种主题生成类人文本方面的能力,显著改变了人工智能的格局。然而,尽管具备令人瞩目的能力,LLMs仍缺乏最新信息,且常使用不精确的语言,这在气候变化等准确性至关重要的领域中是不利的。在本研究中,我们利用近期理念来挖掘LLMs的潜力,将其视为可访问多种来源的智能体,包括包含有关组织、机构和公司最新且精确信息的数据库。我们通过一个原型智能体展示了该方法的有效性,该智能体从ClimateWatch(https://www.climatewatchdata.org/)检索排放数据,并利用常规Google搜索。通过将这些资源与LLMs集成,我们的方法克服了与不精确语言相关的局限性,并在气候变化这一关键领域提供更可靠和准确的信息。这项工作为LLMs的未来发展及其在精度至关重要的领域中的应用铺平了道路。

英文摘要:

Large language models (LLMs) have significantly transformed the landscape of artificial intelligence by demonstrating their ability in generating human-like text across diverse topics. However, despite their impressive capabilities, LLMs lack recent information and often employ imprecise language, which can be detrimental in domains where accuracy is crucial, such as climate change. In this study, we make use of recent ideas to harness the potential of LLMs by viewing them as agents that access multiple sources, including databases containing recent and precise information about organizations, institutions, and companies. We demonstrate the effectiveness of our method through a prototype agent that retrieves emission data from ClimateWatch (https://www.climatewatchdata.org/) and leverages general Google search. By integrating these resources with LLMs, our approach overcomes the limitations associated with imprecise language and delivers more reliable and accurate information in the critical domain of climate change. This work paves the way for future advancements in LLMs and their application in domains where precision is of paramount importance.

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。

↑