EEG Seminar Series -May 10, 2024

The EEG Group will have a joint seminar with the NLIP Group on Friday 10 May. 

Time: 

Lunch will be served from 12:00 to 1:00 pm and the seminar from 1:00 to 2:00 pm. Room FW11 is booked until 3:00 pm for additional discussions.

Location:

The seminar will be held in hybrid mode in Room FW11, William Gates Building, and on Zoom.

Registration:

If you have not registered for your in-person participation, you can join on Zoom or check out this YouTube channel, a recorded video will be uploaded later on Friday. 

Date	Title of Presentation	Speaker Name	Affiliation
10 May	Automated Fact-Checking of Climate Change Claims with Large Language Models	Dominik Stammbach	ETH Zürich

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

Abstract:

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.

For more details, please visit the Talks page.