A new study from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) demonstrates that large language models (LLMs) can be used to automate the process of fact-checking scientific claims. The researchers developed a system called ‘SciCheck’ that uses an LLM to identify check-worthy claims within research papers, retrieve relevant evidence from scientific databases, and then assess the claim’s veracity. The system was tested on claims from biomedical literature and showed promising accuracy, though human oversight remains crucial for nuanced cases. This approach aims to accelerate the review process and help combat the spread of scientific misinformation. For the full details, read the complete article at https://technologyreview.com/2024/05/15/1099875/ai-fact-check-scientific-claims/