CRAFT: A Benchmark for Causal Reasoning About Forces and inTeractions
This benchmark addresses the problem of evaluating causal reasoning in AI models, specifically for understanding physical forces and object interactions, which is a foundational challenge for developing more human-like AI.
This paper introduces CRAFT, a new video question answering dataset with 58K video and question pairs from 10K videos, designed to test causal reasoning about physical forces and object interactions. It includes descriptive, counterfactual, and a new category of causal questions inspired by Force Dynamics Theory. Baseline models, including state-of-the-art methods, struggle with CRAFT, despite its ease for humans.
Humans are able to perceive, understand and reason about causal events. Developing models with similar physical and causal understanding capabilities is a long-standing goal of artificial intelligence. As a step towards this direction, we introduce CRAFT, a new video question answering dataset that requires causal reasoning about physical forces and object interactions. It contains 58K video and question pairs that are generated from 10K videos from 20 different virtual environments, containing various objects in motion that interact with each other and the scene. Two question categories in CRAFT include previously studied descriptive and counterfactual questions. Additionally, inspired by the Force Dynamics Theory in cognitive linguistics, we introduce a new causal question category that involves understanding the causal interactions between objects through notions like cause, enable, and prevent. Our results show that even though the questions in CRAFT are easy for humans, the tested baseline models, including existing state-of-the-art methods, do not yet deal with the challenges posed in our benchmark.