Poster
in
Workshop: ICLR 2025 Workshop on Tackling Climate Change with Machine Learning: Data-Centric Approaches in ML for Climate Action
GreenScreen: Automatic Accessible Presentation Generation from IPCC Reports
Alice Heiman · Komal Vij · Anjali Sreenivas
The Intergovernmental Panel on Climate Change (IPCC) Summary for Policymakers (SPM) is key for communicating climate assessments to leaders and policymakers. However, these SPMs often have poor readability for their target audiences. Research in cognitive theory indicates that more accessible and visual presentations can improve understanding of complex dynamic systems like climate change. AI-driven extractive summarization and content curation have shown promise in fields like medicine and social sciences, leading to calls for its application in climate science, where critical information is often complex to digest despite its urgency. In response, we propose an LLM-driven automated pipeline, GreenScreen, which transforms dense IPCC SPM reports into clear, visual slide decks. This approach makes key climate insights more accessible and actionable. Our results indicate that GreenScreen improves readability from a College Graduate level to a Grade 6 level while preserving an impressive 83% content accuracy.