Pdf Automated Fact Checking Of Climate Claims With Researchgate

npj Climate Action volume 4, Article number: 17 (2025) Cite this article Accurate identification of true versus false climate information in the digital age is critical. Misinformation can significantly affect public understanding and policymaking. Automated fact-checking seeks to validate claims against trustworthy factual data. This study tackles the challenge of fact-checking climate claims by leveraging the currently most capable Large Language Models (LLMs). To this end, we introduce Climinator, an acronym for CLImate Mediator for INformed Analysis and Transparent Objective Reasoning.

It significantly boosts the performance of automated fact-checking by integrating authoritative, up-to-date sources within a novel debating framework. This framework provides a trustworthy and context-aware analysis incorporating multiple scientific viewpoints. Climinator helps identify misinformation in real time and facilitates informed dialog on climate change, highlighting AI’s role in environmental discussions and policy with reliable data. In the era of digital information abundance, the endeavor to counter climate misinformation has found a promising ally in artificial intelligence (AI). Research shows that engaging with an AI chatbot on climate change can significantly align public perception with scientific consensus1, highlighting the importance of ensuring that the large language models (LLMs) underpinning these systems are... Therefore, we ask how well we can embed scientific consensus into automated fact-checking.

To this end, we developed Climinator—an acronym for CLImate Mediator for INformed Analysis and Transparent Objective Reasoning. Climinator evaluates the veracity of climate statements and improves its verdicts with evidence-based and scientifically credible reasoning and references to relevant literature. Our vision is to use AI to catalyze a well-informed global climate dialog, enrich public discourse with scientific insights, and foster a more informed society ready to engage with climate challenges. Climinator serves as a first step in this direction. Platforms like Climate Feedback and Skeptical Science have made commendable efforts to involve climate scientists in volunteering their expertise and providing an essential service in addressing climate misinformation. These scientists voluntarily dedicate their time to giving concise science-based evaluations, including references, and delivering a final verdict on disputed claims.

Despite their valuable contributions, these efforts face significant challenges, including scalability and actuality. Hence, their impact is limited by the sheer volume of misinformation and skepticism in digital media, worsened by misinformation spreading more rapidly and widely than factual information2. As a response, automated fact-checking3,4 aims to debunk misinformation at scale using natural language processing methods. While automated fact-checking tools have improved, they struggle with complex claims due to a lack of detailed reasoning5,6,7, particularly in the domain of climate change8. To address this problem, we introduce an advanced framework that overcomes these limitations by integrating LLMs within a Mediator-Advocate model. Although recent work has explored the aggregation of different viewpoints using LLMs to build a general consensus9, we address real-world claim complexities and evidence controversies in a novel way10,11,12.

In particular, we introduce separate “Advocates,” each drawing on a distinct text corpus to represent a specific viewpoint, while a “Mediator” either asks follow-up questions or synthesizes these perspectives into a cohesive and balanced... arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Accurate identification of true versus false climate information in the digital age is critical. Misinformation can significantly affect public understanding and policymaking. Automated fact-checking seeks to validate claims against trustworthy factual data. This study tackles the challenge of fact-checking climate claims by leveraging the currently most capable Large Language Models (LLMs). To this end, we introduce Climinator, an acronym for CLImate Mediator for INformed Analysis and Transparent Objective Reasoning. It significantly boosts the performance of automated fact-checking by integrating authoritative, up-to-date sources within a novel debating framework.

This framework provides a trustworthy and context-aware analysis incorporating multiple scientific viewpoints. Climinator helps identify misinformation in real time and facilitates informed dialog on climate change, highlighting AI's role in environmental discussions and policy with reliable data. Keywords: Climate sciences; Communication; Education; Environmental social sciences. Competing interestsThe authors declare no competing interests. Fig. 1.

Performance in terms of accuracy… Fig. 1. Performance in terms of accuracy (averaged micro-F1) of various models in classifying Climate… 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. 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.

In the ongoing debate on climate change, the truthfulness of public statements is regularly called into question, emphasizing the critical need for swift and reliable fact-checking. A case in point is the recent claim made by Sultan Al Jaber, the president of COP28 and chief executive of the United Arab Emirates’ state oil company Adnoc. On November 21, 2023, Al Jaber controversially asserted that “There is no science out there, or no scenario out there, that says that the phase-out of fossil fuel is what’s going to achieve 1.5C.”... Recognizing this challenge, our paper introduces Climinator, a novel framework designed to assess climate-related claims, leveraging advancements in LLMs. Climinator -– an acronym for CLImate Mediator for INformed Analysis and Transparent Objective Reasoning -– not only evaluates the accuracy of statements but also enhances its verdicts with evidence-based reasoning and relevant literature references. In an era where information proliferates at an unprecedented pace, the task of manually reviewing claims for accuracy becomes increasingly resource-intensive and challenging.

Over a decade ago, scholars warned that the exponential growth of online content would eventually overwhelm journalistic fact-checkers, diminishing news quality and contributing to societal harms like diminished government accountability (Cohen et al. 2011). This concern has given rise to a new strand of research in Natural Language Processing (NLP), namely automated fact-checking (Cohen et al. 2011; Vlachos and Riedel 2014a; Hassan et al. 2017; Graves 2018; Guo, Schlichtkrull, and Vlachos 2022). With misinformation spreading faster and deeper than factual news (Vosoughi, Roy, and Aral 2018), there is a pressing need for sophisticated tools capable of effective and real-time fact-checking.

While early automated fact-checking tools, such as those based on the FEVER dataset (Thorne et al. 2018) and climate-focused datasets like climateFEVER (Diggelmann et al. 2020), have made significant progress, they often fall short in providing the nuanced reasoning necessary for a comprehensive understanding of complex claims. This is where generative AI models, specifically LLMs, come into play. LLMs can offer holistic evaluations rooted in an extensive scientific knowledge base. They can provide the necessary context, reasoning, and argumentation essential for reaching well-informed verdicts on complex climate-related claims.

Building on this premise, Climinator leverages the capabilities of LLMs to evaluate climate-related claims based on empirical evidence and scientific consensus. The aim is to provide a comprehensive, transparent, and objective assessment of claims that is not limited to countering polarized views but rather enables a more nuanced understanding of climate issues. Figure 1 depicts the operational flow of the Climinator framework, where the initial claim is parsed by an LLM into subclaims, enhancing the specificity and efficiency of the evaluation process. Specialized LLMs, henceforth referred to as advocates, are pivotal in the next phase. Each advocate examines the claim against a curated corpus of texts. The general GPT-4 model (OpenAI 2023) serves as one Advocate, while other advocates consist of retrieval-augmented generation (RAG) systems.

These systems, which ensure LLM responses are grounded in credible sources, draw from diverse scientific and trusted repositories: the Intergovernmental Panel on Climate Change (IPCC) AR6 reports, World Meteorological Organization (WMO) sources, and two... We describe the data in Section A. Each of the advocates is grounded on one particular text corpus and delivers a verdict informed by its respective data sources, prompted to provide evidence-backed rationales.

People Also Search

• (PDF) Automated fact-checking of climate claims with ... - ResearchGate
• Automated fact-checking of climate claims with large language models
• [2401.12566] Automated Fact-Checking of Climate Change Claims with ...
• Automated Fact-Checking of Climate Change Claims with Large Language ...
• (PDF) Fact-Checking Climate Change: An Analysis of Claims and ...
• PDF Automated fact-checking of climate claims with large ... - ResearchGate
• (PDF) Automatic Claim Review for Climate Science via ... - ResearchGate
• Automated Fact-Checking of Climate Change Claims with Large Language Models