A self-supervised language model selection strategy for biomedical question answering.

Large neural-based Pre-trained Language Models (PLM) have recently gained much attention due to their noteworthy performance in many downstream Information Retrieval (IR) and Natural Language Processing (NLP) tasks. PLMs can be categorized as either general-purpose, which are trained on resources such as large-scale Web corpora, and domain-specific which are trained on in-domain or mixed-domain corpora. While domain-specific PLMs have shown promising performance on domain-specific tasks, they are significantly more computationally expensive compared to general-purpose PLMs as they have to be either retrained or trained from scratch. The objective of our work in this paper is to explore whether it would be possible to leverage general-purpose PLMs to show competitive performance to domain-specific PLMs without the need for expensive retraining of the PLMs for domain-specific tasks. By focusing specifically on the recent BioASQ Biomedical Question Answering task, we show how different general-purpose PLMs show synergistic behaviour in terms of performance, which can lead to overall notable performance improvement when used in tandem with each other. More concretely, given a set of general-purpose PLMs, we propose a self-supervised method for training a classifier that systematically selects the PLM that is most likely to answer the question correctly on a per-input basis. We show that through such a selection strategy, the performance of general-purpose PLMs can become competitive with domain-specific PLMs while remaining computationally light since there is no need to retrain the large language model itself. We run experiments on the BioASQ dataset, which is a large-scale biomedical question-answering benchmark. We show that utilizing our proposed selection strategy can show statistically significant performance improvements on general-purpose language models with an average of 16.7% when using only lighter models such as DistilBERT and DistilRoBERTa, as well as 14.2% improvement when using relatively larger models such as BERT and RoBERTa and so, their performance become competitive with domain-specific large language models such as PubMedBERT.