Logical Reasoning over Natural Language as Knowledge Representation: A Survey

TL;DR

This survey explores a new paradigm of logical reasoning in AI that uses natural language and pretrained language models, addressing limitations of formal language approaches and highlighting recent advances with transformer-based models.

Contribution

It provides a comprehensive overview of natural language-based logical reasoning, including definitions, advantages, benchmarks, methods, challenges, and future directions.

Findings

Natural language reasoning alleviates formal language limitations.

Transformer-based models enable reasoning over English.

The paradigm shows promise over traditional neural methods.

Abstract

Logical reasoning is central to human cognition and intelligence. It includes deductive, inductive, and abductive reasoning. Past research of logical reasoning within AI uses formal language as knowledge representation and symbolic reasoners. However, reasoning with formal language has proved challenging (e.g., brittleness and knowledge-acquisition bottleneck). This paper provides a comprehensive overview on a new paradigm of logical reasoning, which uses natural language as knowledge representation and pretrained language models as reasoners, including philosophical definition and categorization of logical reasoning, advantages of the new paradigm, benchmarks and methods, challenges of the new paradigm, possible future directions, and relation to related NLP fields. This new paradigm is promising since it not only alleviates many challenges of formal representation but also has advantages over end-to-end neural methods. This survey focus on transformer-based LLMs explicitly working on deductive, inductive, and abductive reasoning over English representation.