NEWTON: Are Large Language Models Capable of Physical Reasoning? abs: arxiv.org/pdf/2310.07018… pdf: arxiv.org/pdf/2310.07018… website: newtonreasoning.github.io NEWTON repository: consists of labeled object-centric data, crowd-sourced for 700+ objects across 8 physical attributes NEWTON pipeline: introduces a method for systematically generating infinite evaluation questions tailored to specific use cases. #nlp #llms