Existing pre-trained transformer analysis works usually focus only on one or two model families at a time, overlooking the variability of the architecture and pre-training objectives. In our work, we utilize the oLMpics benchmark and psycholinguistic probing datasets for a diverse set of 29 models including T5, BART, and ALBERT. Additionally, we adapt the oLMpics zero-shot setup for autoregressive models and evaluate GPT networks of different sizes. Our findings show that none of these models can resolve compositional questions in a zero-shot fashion, suggesting that this skill is not learnable using existing pre-training objectives. Furthermore, we find that global model decisions such as architecture, directionality, size of the dataset, and pre-training objective are not predictive of a model's linguistic capabilities.
@article{arxiv.2205.10696,
title = {Life after BERT: What do Other Muppets Understand about Language?},
author = {Vladislav Lialin and Kevin Zhao and Namrata Shivagunde and Anna Rumshisky},
journal= {arXiv preprint arXiv:2205.10696},
year = {2022}
}