3 papers
cs.CL2024
Hierarchical Skip Decoding for Efficient Autoregressive Text Generation
Yunqi Zhu, Xuebing Yang, Yuanyuan Wu +1
Autoregressive decoding strategy is a commonly used method for text generation tasks with pre-trained language models, while early-exiting is an effective approach to speedup the i…
cs.CL2023
Parameter-Efficient Fine-Tuning with Layer Pruning on Free-Text Sequence-to-Sequence Modeling
Yunqi Zhu, Xuebing Yang, Yuanyuan Wu +1
The increasing size of language models raises great research interests in parameter-efficient fine-tuning such as LoRA that freezes the pre-trained model, and injects small-scale t…
cs.CL2023
Leveraging Summary Guidance on Medical Report Summarization
Yunqi Zhu, Xuebing Yang, Yuanyuan Wu +1
This study presents three deidentified large medical text datasets, named DISCHARGE, ECHO and RADIOLOGY, which contain 50K, 16K and 378K pairs of report and summary that are derive…