A Systematic Investigation of Commonsense Knowledge in Large Language Models
This work addresses the problem of assessing commonsense knowledge in language models for NLP applications, but it is incremental as it builds on existing evaluation methods.
The paper systematically evaluated large pre-trained language models on commonsense knowledge tasks under zero-shot and few-shot setups, finding that these models have limitations in acquiring commonsense knowledge without supervision and fail to achieve human-level performance even with larger models or few-shot evaluation.
Language models (LMs) trained on large amounts of data have shown impressive performance on many NLP tasks under the zero-shot and few-shot setup. Here we aim to better understand the extent to which such models learn commonsense knowledge -- a critical component of many NLP applications. We conduct a systematic and rigorous zero-shot and few-shot commonsense evaluation of large pre-trained LMs, where we: (i) carefully control for the LMs' ability to exploit potential surface cues and annotation artefacts, and (ii) account for variations in performance that arise from factors that are not related to commonsense knowledge. Our findings highlight the limitations of pre-trained LMs in acquiring commonsense knowledge without task-specific supervision; furthermore, using larger models or few-shot evaluation are insufficient to achieve human-level commonsense performance.