15 citations · 18 across the 3 of their papers we have counts for
4 papers
DySpec: Faster Speculative Decoding with Dynamic Token Tree Structure
Yunfan Xiong, Ruoyu Zhang, Yanzeng Li +2
While speculative decoding has recently appeared as a promising direction for accelerating the inference of large language models (LLMs), the speedup and scalability are strongly b…
Leveraging Large Language Model as Simulated Patients for Clinical Education
Yanzeng Li, Cheng Zeng, Jialun Zhong +3
Simulated Patients (SPs) play a crucial role in clinical medical education by providing realistic scenarios for student practice. However, the high cost of training and hiring qual…
LLMaAA: Making Large Language Models as Active Annotators
Ruoyu Zhang, Yanzeng Li, Yongliang Ma +2
Prevalent supervised learning methods in natural language processing (NLP) are notoriously data-hungry, which demand large amounts of high-quality annotated data. In practice, acqu…
Two is Better Than One: Answering Complex Questions by Multiple Knowledge Sources with Generalized Links
Minhao Zhang, Yongliang Ma, Yanzeng Li +3
Incorporating multiple knowledge sources is proven to be beneficial for answering complex factoid questions. To utilize multiple knowledge bases (KB), previous works merge all KBs…