Abstract Pretrained Foundation Models (PFMs) are regarded as the foundation for various
downstream tasks across different data modalities. A PFM (eg, BERT, ChatGPT, GPT-4) is …

Nowadays, in the globalised context in which we find ourselves, language barriers can still
be an obstacle to accessing information. On occasions, it is impossible to satisfy the demand …

Foundation models are first pre-trained on vast unsupervised datasets and then fine-tuned
on labeled data. Reinforcement learning, notably from human feedback (RLHF), can further …

A wide variety of NLP applications, such as machine translation, summarization, and dialog,
involve text generation. One major challenge for these applications is how to evaluate …

Recent advancements in large language models (LLMs) have transformed the field of
question answering (QA). However, evaluating LLMs in the medical field is challenging due …

Automatically generating radiology reports can improve current clinical practice in diagnostic
radiology. On one hand, it can relieve radiologists from the heavy burden of report writing; …

It is well known that the standard likelihood training and approximate decoding objectives in
neural text generation models lead to less human-like responses for open-ended tasks such …

Text preprocessing is not only an essential step to prepare the corpus for modeling but also
a key area that directly affects the natural language processing (NLP) application results. For …

This paper creates a paradigm shift with regard to the way we build neural extractive
summarization systems. Instead of following the commonly used framework of extracting …

The dominant paradigm for neural text generation is left-to-right decoding from
autoregressive language models. Constrained or controllable generation under complex …