13 papers
Structured Gradient Guidance for Few-Shot Adaptation in Large Language Models
Hongye Zheng, Yichen Wang, Ray Pan +3
This paper presents a gradient-informed fine-tuning method for large language models under few-shot conditions. The goal is to enhance task adaptability and training stability when…
Context-Guided Dynamic Retrieval for Improving Generation Quality in RAG Models
Jacky He, Guiran Liu, Binrong Zhu +3
This paper focuses on the dynamic optimization of the Retrieval-Augmented Generation (RAG) architecture. It proposes a state-aware dynamic knowledge retrieval mechanism to enhance…
Pre-trained Language Models and Few-shot Learning for Medical Entity Extraction
Xiaokai Wang, Guiran Liu, Binrong Zhu +3
This study proposes a medical entity extraction method based on Transformer to enhance the information extraction capability of medical literature. Considering the professionalism…
Semantic and Contextual Modeling for Malicious Comment Detection with BERT-BiLSTM
Zhou Fang, Hanlu Zhang, Jacky He +2
This study aims to develop an efficient and accurate model for detecting malicious comments, addressing the increasingly severe issue of false and harmful content on social media p…
A LongFormer-Based Framework for Accurate and Efficient Medical Text Summarization
Dan Sun, Jacky He, Hanlu Zhang +3
This paper proposes a medical text summarization method based on LongFormer, aimed at addressing the challenges faced by existing models when processing long medical texts. Traditi…
A Fine-Tuning Approach for T5 Using Knowledge Graphs to Address Complex Tasks
Xiaoxuan Liao, Binrong Zhu, Jacky He +3
With the development of deep learning technology, large language models have achieved remarkable results in many natural language processing tasks. However, these models still have…