The Odyssey of Commonsense Causality: From Foundational Benchmarks to Cutting-Edge Reasoning
This is an incremental survey that organizes existing knowledge to benefit scholars and beginners in AI and related fields like law, where commonsense causality is crucial for tasks such as legal liability determination.
The paper addresses the lack of systematic exploration in commonsense causality by conducting a comprehensive survey that synthesizes insights from over 200 articles, covering taxonomies, benchmarks, acquisition methods, and reasoning approaches to provide an overview and guide for researchers.
Understanding commonsense causality is a unique mark of intelligence for humans. It helps people understand the principles of the real world better and benefits the decision-making process related to causation. For instance, commonsense causality is crucial in judging whether a defendant's action causes the plaintiff's loss in determining legal liability. Despite its significance, a systematic exploration of this topic is notably lacking. Our comprehensive survey bridges this gap by focusing on taxonomies, benchmarks, acquisition methods, qualitative reasoning, and quantitative measurements in commonsense causality, synthesizing insights from over 200 representative articles. Our work aims to provide a systematic overview, update scholars on recent advancements, provide a pragmatic guide for beginners, and highlight promising future research directions in this vital field.