Pre-trained language models (PLMs) have been the de facto paradigm for most natural
language processing tasks. This also benefits the biomedical domain: researchers from …

Artificial intelligence (AI), especially the most recent large language models (LLMs), holds
great promise in healthcare and medicine, with applications spanning from biological …

Scientific literature understanding tasks have gained significant attention due to their
potential to accelerate scientific discovery. Pre-trained language models (LMs) have shown …

The exponential growth of biomedical texts such as biomedical literature and electronic
health records (EHRs), poses a significant challenge for clinicians and researchers to …

Abstract Automatically Impression Generation (AIG) can conclude essential information of
the “Findings” section, thus facilitating more effective communication between radiographers …

Contrastive learning has recently been introduced into neural topic models (NTMs) to
improve latent semantic discovery, but existing methods suffer from the sample bias problem …

Abstractive summarization of scientific papers has always been a research focus, yet
existing methods face two main challenges. First, most summarization models rely on …

With the advent of large language models (LLMs), managing scientific literature via LLMs
has become a promising direction of research. However, existing approaches often overlook …

Existing NTMs with contrastive learning suffer from the sample bias problem owing to the
word frequency-based sampling strategy, which may result in false negative samples with …

With the development of information technology, a large amount of information and corpora
has been incrementally sparked from the Web, stimulating an increasingly high demand for …