ImmunoFOMO: Are Language Models missing what oncologists see?
This work addresses the problem of evaluating language models' medical understanding for oncologists, but it is incremental as it focuses on a specific domain task.
The paper investigated the medical conceptual grounding of language models compared to expert clinicians for identifying immunotherapy hallmarks in breast cancer abstracts, finding that pre-trained language models can outperform large language models in identifying specific low-level concepts.
Language models (LMs) capabilities have grown with a fast pace over the past decade leading researchers in various disciplines, such as biomedical research, to increasingly explore the utility of LMs in their day-to-day applications. Domain specific language models have already been in use for biomedical natural language processing (NLP) applications. Recently however, the interest has grown towards medical language models and their understanding capabilities. In this paper, we investigate the medical conceptual grounding of various language models against expert clinicians for identification of hallmarks of immunotherapy in breast cancer abstracts. Our results show that pre-trained language models have potential to outperform large language models in identifying very specific (low-level) concepts.