The Odyssey of Commonsense Causality: From Foundational Benchmarks to Cutting-Edge Reasoning

TL;DR

This paper provides a comprehensive survey of commonsense causality, covering taxonomies, benchmarks, methods, and recent advancements to guide future research and understanding in this vital area of AI.

Contribution

It systematically synthesizes over 200 articles on commonsense causality, offering an organized overview and identifying future research directions.

Findings

Extensive taxonomy of commonsense causality

Evaluation benchmarks and acquisition methods

Recent advancements in reasoning techniques

Abstract

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.