PaCo: Preconditions Attributed to Commonsense Knowledge
This addresses a key limitation in AI's commonsense reasoning for applications like natural language understanding, though it is incremental as it focuses on a specific gap rather than a broad breakthrough.
The paper tackles the problem of whether language models can understand circumstantial preconditions in commonsense reasoning, revealing a 10-30% performance gap between machines and humans on new evaluation tasks.
Humans can seamlessly reason with circumstantial preconditions of commonsense knowledge. We understand that a glass is used for drinking water, unless the glass is broken or the water is toxic. Despite state-of-the-art (SOTA) language models' (LMs) impressive performance on inferring commonsense knowledge, it is unclear whether they understand the circumstantial preconditions. To address this gap, we propose a novel challenge of reasoning with circumstantial preconditions. We collect a dataset, called PaCo, consisting of 12.4 thousand preconditions of commonsense statements expressed in natural language. Based on this dataset, we create three canonical evaluation tasks and use them to examine the capability of existing LMs to understand situational preconditions. Our results reveal a 10-30% gap between machine and human performance on our tasks, which shows that reasoning with preconditions is an open challenge.