Large Language Models (LLMs) have exhibited remarkable proficiency across a wide array
of NLP tasks. However, the escalation in model size also engenders substantial deployment …

This work presents a dynamic vocabulary adaptation strategy, MEDVOC, for fine-tuning pre-
trained language models (PLMs) like BertSumAbs, BART, and PEGASUS for improved …

In this work, we show a fundamental limitation in vocabulary adaptation approaches that use
Byte-Pair Encoding (BPE) tokenization scheme for fine-tuning pretrained language models …

Learning high-quality text embedding is vital for biomedical topic classification and many
other NLP tasks. Contrastive learning has shown remarkable performance in generating …