While large language models (LLMs) like ChatGPT have shown impressive capabilities in
Natural Language Processing (NLP) tasks, a systematic investigation of their potential in this …

For long document summarization, discourse structure is important to discern the key
content of the text and the differences in importance level between sentences. Unfortunately …

The current safeguard mechanisms for large language models (LLMs) are indeed
susceptible to jailbreak attacks, making them inherently fragile. Even the process of fine …

Large language models (LLMs) with billions of parameters and pretrained on massive
amounts of data are now capable of near or better than state-of-the-art performance in a …

Pre-trained language models (PLMs) show impressive performance in various downstream
NLP tasks. However, pre-training large language models demands substantial memory and …

Parameter-efficient fine-tuning (PEFT) methods are increasingly vital in adapting large-scale
pre-trained language models for diverse tasks, offering a balance between adaptability and …

Multi-task learning (MTL) approach leverages pre-trained models in speech and machine
translation and has significantly advanced speech-to-text translation tasks. However, it …