Rule or Story, Which is a Better Commonsense Expression for Talking with Large Language Models?

arXiv:2402.14355v1 Announce Type: new
Abstract: Building machines with commonsense has been a longstanding challenge in NLP due to the reporting bias of commonsense rules and the exposure bias of rule-based commonsense reasoning. In contrast, humans convey and pass down commonsense implicitly through stories. This paper investigates the inherent commonsense ability of large language models (LLMs) expressed through storytelling. We systematically investigate and compare stories and rules for retrieving and leveraging commonsense in LLMs. Experimental results on 28 commonsense QA datasets …

abstract arxiv bias building challenge contrast cs.cl humans language language models large language large language models machines nlp paper reasoning reporting rules stories story through type