Concise and Organized Perception Facilitates Large Language Models for Deductive Reasoning

arXiv:2310.03309v2 Announce Type: replace
Abstract: Exploiting large language models (LLMs) to tackle deductive reasoning has garnered growing attention. It still remains highly challenging to achieve satisfactory results in complex deductive problems, characterized by plenty of premises (i.e., facts or rules) entailing intricate relationships among entities and requiring multi-hop reasoning. One intuitive solution is to decompose the original task into smaller sub-tasks, and then chain the multiple casual reasoning steps together in a forward (e.g., Selection-Inference) or backward (e.g., LAMBADA) direction. …

abstract arxiv attention cs.ai cs.cl facts language language models large language large language models llms perception reasoning relationships results rules type