ChatClimate: Grounding Conversational AI in Climate Science

22 Pages Posted: 26 Apr 2023 Last revised: 9 Oct 2023

See all articles by Saeid Vaghefi

Saeid Vaghefi

University of Zurich

Qian Wang

University of Zurich - Department Finance; Inovest Partners AG

Veruska Muccione

University of Zurich - Department of Geography; University of Geneva - Institute for Environmental Sciences

Jingwei Ni

ETH Zurich

Mathias Kraus

University of Erlangen-Nuremberg-Friedrich Alexander Universität Erlangen Nürnberg

Julia Bingler

University of Oxford

Tobias Schimanski

University of Zurich

Chiara Colesanti Senni

University of Zurich - Department of Finance

Nicolas Webersinke

Friedrich-Alexander-Universität Erlangen-Nürnberg

Christian Huggel

University of Zurich

Markus Leippold

University of Zurich; Swiss Finance Institute

Date Written: April 11, 2023

Abstract

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 However, they still face two major challenges: hallucination and outdated information after the training phase.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(long-term memory) to continuously update their knowledge and prevent the propagation of inaccurate, incorrect, or outdated information.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, for his invaluable and voluntary support in setting up the server. The server will become available by mid-April.} and demonstrate its ability to answer challenging questions accurately. 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.

Suggested Citation

Vaghefi, Saeid and Wang, Qian and Muccione, Veruska and Ni, Jingwei and Kraus, Mathias and Bingler, Julia and Schimanski, Tobias and Colesanti Senni, Chiara and Webersinke, Nicolas and Huggel, Christian and Leippold, Markus, ChatClimate: Grounding Conversational AI in Climate Science (April 11, 2023). Swiss Finance Institute Research Paper No. 23-88, Available at SSRN: https://ssrn.com/abstract=4414628 or http://dx.doi.org/10.2139/ssrn.4414628

Saeid Vaghefi

University of Zurich ( email )

Qian Wang

University of Zurich - Department Finance ( email )

Schönberggasse 1
Zürich, 8001
Switzerland

Inovest Partners AG ( email )

Grabenstrasse 25
Baar, 6340
Switzerland

Veruska Muccione

University of Zurich - Department of Geography ( email )

University of Geneva - Institute for Environmental Sciences ( email )

Jingwei Ni

ETH Zurich ( email )

Mathias Kraus

University of Erlangen-Nuremberg-Friedrich Alexander Universität Erlangen Nürnberg ( email )

Schloßplatz 4
Erlangen, DE Bavaria 91054
Germany

Julia Bingler

University of Oxford ( email )

Mansfield Road
Oxford, Oxfordshire OX1 4AU
United Kingdom

Tobias Schimanski

University of Zurich ( email )

Schönberggasse 1
Zürich, 8001
Switzerland

Chiara Colesanti Senni

University of Zurich - Department of Finance ( email )

Plattenstr 32
Zurich, 8032
Switzerland

Nicolas Webersinke

Friedrich-Alexander-Universität Erlangen-Nürnberg ( email )

Lange Gasse 20
Lange Gasse 20,
Nürnberg, 90403
Germany

Christian Huggel

University of Zurich ( email )

Markus Leippold (Contact Author)

University of Zurich ( email )

Rämistrasse 71
Zürich, CH-8006
Switzerland

Swiss Finance Institute ( email )

c/o University of Geneva
40, Bd du Pont-d'Arve
CH-1211 Geneva 4
Switzerland

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
1,945
Abstract Views
6,661
Rank
15,973
PlumX Metrics