Are Prompt-based Models Clueless?

Abstract

Pretrained language models have achieved remarkable performance on most of the natural language benchmarks. Until recently, the dominant approach of adapting these models to downstream tasks has been through finetuning a task-specific head. But, previous work has found that these models learn to exploit spurious correlations between inputs and the labels (Gururangan et al. 2018;Poliak et al. 2018;Kavumba et al. 2019). These spurious correlations may exist in the form of unique input tokens or style or annotation artifacts, which all fall under the wide umbrella of superficial cues (Kavumba et al. 2019). While superficial cues are strong predictors of the labels, they have nothing to do with the intended task. In software development, superficial cues can be viewed as bugs in the task design. They enable the task to be solved in non-intended ways, hence the dataset becomes a poor benchmark of the required ability or abilities. In causality, we can view superficial cues as confounding variables. Unfortunately, superficial cues tend to be unique to a single dataset. Thus, the model's remarkable performance on one dataset does not transfer to other datasets, i.e., the models tend not to be robust. In order to develop models that are truly robust, we need to identify and examine if the models are exploiting superficial cues. This is the first step to debug both the dataset and the model's. Only then can we train robust models that learn to be right for the right reasons (Kavumba et al. 2021).Recently, prompting has been shown to achieve competitive performance to models finetuned using a task-specific head. This is despite using a few task-specific finetuning examples. Given the little data that prompt-based models require to achieve optimal performance on downstream tasks, do they also learn to exploit superficial cues? Thus, we asked, Do prompt-based models exploit superficial cues? This is the research question explored in Kavumba et al. (2022). We presented a rigorous empirical investigation of prompt-based models and whether or not they also exploit superficial cues. We examined prompted-based models on two English language fundamental tasks of natural language understanding: natural language inference (NLI) and

State-of-the-art generalisation research in NLP: A taxonomy and review

“…An example of this category would be a test that investigates how well one pretrained model generalises with respect to an o.o.d. finetuning train-test split(Damonte and Monti, 2021;Kavumba et al, 2022;Ludwig et al, 2022). The parts of the modelling pipeline that studies with a finetune train-test locus can evaluate are the same as studies with a train-test locus, although studies that investigate the generalisation abilities of a single finetuned model instance are rare.…”