Automated Fact-Checking of Climate Change Claims with Large Language Models

42 Pages Posted: 8 Mar 2024

See all articles by Markus Leippold

Markus Leippold

University of Zurich; Swiss Finance Institute

Saeid Vaghefi

University of Zurich

Veruska Muccione

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

Julia Bingler

University of Oxford

Dominik Stammbach

ETH Zürich

Chiara Colesanti Senni

University of Zurich - Department of Finance

Jingwei Ni

ETH Zurich

Tobias Wekhof

ETH Zürich - CER-ETH - Center of Economic Research at ETH Zurich

Tingyu Yu

University of Zurich - Department Finance

Tobias Schimanski

University of Zurich

Glen Gostlow

University of Zurich - Department Finance

Jürg Luterbacher

World Health Organization (WHO) - World Health Organization, Geneva

Christian Huggel

University of Zurich

Date Written: February 19, 2024

Abstract

This paper presents Climinator, a novel AI-based tool designed to automate the fact-checking of climate change claims. Utilizing an array of Large Language Models (LLMs) informed by authoritative sources like the IPCC reports and peer-reviewed scientific literature, Climinator employs an innovative Mediator-Advocate framework. This design allows Climinator to effectively synthesize varying scientific perspectives, leading to robust, evidence-based evaluations. Our model demonstrates remarkable accuracy when testing claims collected from Climate Feedback and Skeptical Science. Notably, when integrating an advocate with a climate science denial perspective in our framework, Climinator's iterative debate process reliably converges towards scientific consensus, underscoring its adeptness at reconciling diverse viewpoints into science-based, factual conclusions. While our research is subject to certain limitations and necessitates careful interpretation, our approach holds significant potential. We hope to stimulate further research and encourage exploring its applicability in other contexts, including political fact-checking and legal domains.

Suggested Citation

Leippold, Markus and Vaghefi, Saeid and Muccione, Veruska and Bingler, Julia and Stammbach, Dominik and Colesanti Senni, Chiara and Ni, Jingwei and Wekhof, Tobias and Yu, Tingyu and Schimanski, Tobias and Gostlow, Glen and Luterbacher, Jürg and Huggel, Christian, Automated Fact-Checking of Climate Change Claims with Large Language Models (February 19, 2024). Available at SSRN: https://ssrn.com/abstract=4731802 or http://dx.doi.org/10.2139/ssrn.4731802

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

Saeid Vaghefi

University of Zurich ( email )

Veruska Muccione

University of Zurich - Department of Geography ( email )

University of Geneva - Institute for Environmental Sciences ( email )

Julia Bingler

University of Oxford ( email )

Mansfield Road
Oxford, Oxfordshire OX1 4AU
United Kingdom

Dominik Stammbach

ETH Zürich ( email )

Zürichbergstrasse 18
8092 Zurich, CH-1015
Switzerland

Chiara Colesanti Senni

University of Zurich - Department of Finance ( email )

Plattenstr 32
Zurich, 8032
Switzerland

Jingwei Ni

ETH Zurich ( email )

Tobias Wekhof

ETH Zürich - CER-ETH - Center of Economic Research at ETH Zurich ( email )

Zürichbergstrasse 18
Zurich, 8092
Switzerland
+41 44 633 80 78 (Phone)

HOME PAGE: http://sites.google.com/view/tobiaswekhof

Tingyu Yu

University of Zurich - Department Finance ( email )

Schönberggasse 1
Zürich, 8001
Switzerland

Tobias Schimanski

University of Zurich ( email )

Schönberggasse 1
Zürich, 8001
Switzerland

Glen Gostlow

University of Zurich - Department Finance ( email )

Schönberggasse 1
Zürich, 8001
Switzerland

Jürg Luterbacher

World Health Organization (WHO) - World Health Organization, Geneva ( email )

Christian Huggel

University of Zurich ( email )

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

Paper statistics

Downloads
79
Abstract Views
337
Rank
575,940
PlumX Metrics