AI RESEARCH
Estimating Commonsense Plausibility through Semantic Shifts
arXiv CS.CL
•
ArXi:2502.13464v2 Announce Type: replace Commonsense plausibility estimation is critical for evaluating language models (LMs), yet existing generative approaches--reliant on likelihoods or verbalized judgments--struggle with fine-grained discrimination. In this paper, we propose ComPaSS, a novel discriminative framework that quantifies commonsense plausibility by measuring semantic shifts when augmenting sentences with commonsense-related information. Plausible augmentations induce minimal shifts in semantics, while implausible ones result in substantial deviations.