Logical Negation Augmenting and Debiasing for Prompt-based Methods

arXiv:2405.04872v1 Announce Type: new
Abstract: Prompt-based methods have gained increasing attention on NLP and shown validity on many downstream tasks. Many works have focused on mining these methods' potential for knowledge extraction, but few explore their ability to make logical reasoning. In this work, we focus on the effectiveness of the prompt-based methods on first-order logical reasoning and find that the bottleneck lies in logical negation. Based on our analysis, logical negation tends to result in spurious correlations to negative …

abstract arxiv attention cs.ai cs.cl cs.lo explore extraction focus knowledge mining nlp prompt reasoning tasks the prompt type work