Logical Reasoning over Natural Language as Knowledge Representation: A Survey
It addresses the brittleness and knowledge-acquisition bottleneck in AI logical reasoning for researchers in NLP and AI, but is incremental as it surveys existing work rather than proposing new methods.
This survey tackles the challenge of logical reasoning in AI by reviewing a new paradigm that uses natural language as knowledge representation and pretrained language models as reasoners, highlighting its advantages over formal language and end-to-end neural methods.
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.