Towards Zero-shot Commonsense Reasoning with Self-supervised Refinement of Language Models

Abstract: Can we get existing LLMs and refine them for zero-shot commonsense reasoning? This paper presents an initial study exploring the feasibility of zero-shot commonsense reasoning for the Winograd Schema Challenge by formulating the task as self-supervised refinement of a pre-trained LLM. In contrast to previous studies that rely on fine-tuning annotated datasets, we seek to boost conceptualization via loss landscape refinement. To this end, we propose a novel self-supervised learning approach that refines the LLM utilizing a set of linguistic perturbations of similar concept relationships. Empirical analysis of our conceptually simple framework demonstrates the viability of zero-shot commonsense reasoning on multiple benchmarks.