Estimating Commonsense Plausibility through Semantic Shifts

Wanqing Cui, Keping Bi, Jiafeng Guo, Xueqi Cheng

Keywords: commonsense, evaluation methodologies, evaluation

TL;DR: We propose a fine-grained commonsense plausibility estimation method with semantic shifts from the discriminative perspective.

Abstract:

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. Evaluations on two types of fine-grained commonsense plausibility estimation tasks across varying input formats and commonsense
knowledge levels based on different backbones, including LLMs and vision-language models (VLMs), show that ComPaSS consistently outperforms baselines. It demonstrates the advantage of discriminative approaches over generative methods in fine-grained commonsense plausibility evaluation. Experiments also show that (1) VLMs yield superior performance to LMs, when integrated with ComPaSS, on vision-grounded commonsense tasks. (2) contrastive pre-training sharpens backbone models' ability to capture semantic nuances, thereby further enhancing ComPaSS.

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 24515