Скачать с ютуб Automated Fact-Checking of Climate Change Claims with Large Language Models в хорошем качестве

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

This talk introduces 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. Bio: Dominik Stammbach just recently finished his PhD in Natural Language Processing at ETH Zurich and is an incoming postdoc at Princeton University in Fall 2024. Dominik's research interests include developing NLP methods which can be applied in the context of misinformation, online safety and developing methods at the intersection NLP and climate change. Among others, he wants to detect company greenwashing, the practice of companies making generic, misleading or false claims to boost their environmental credentials.