Prompt as triggers for backdoor attack: Examining the vulnerability in language models
The prompt-based learning paradigm, which bridges the gap between pre-training and fine-
tuning, achieves state-of-the-art performance on several NLP tasks, particularly in few-shot …
tuning, achieves state-of-the-art performance on several NLP tasks, particularly in few-shot …
DAE-NER: Dual-channel attention enhancement for Chinese named entity recognition
J Liu, M Sun, W Zhang, G Xie, Y Jing, X Li… - Computer Speech & …, 2024 - Elsevier
Abstract Named Entity Recognition (NER) is an important component of Natural Language
Processing (NLP) and is a fundamental yet challenging task in text analysis. Recently, NER …
Processing (NLP) and is a fundamental yet challenging task in text analysis. Recently, NER …
From softmax to nucleusmax: A novel sparse language model for chinese radiology report summarization
The Chinese radiology report summarization is a crucial component in smart healthcare that
employs language models to summarize key findings in radiology reports and communicate …
employs language models to summarize key findings in radiology reports and communicate …
[PDF][PDF] Universal vulnerabilities in large language models: Backdoor attacks for in-context learning
In-context learning, a paradigm bridging the gap between pre-training and fine-tuning, has
demonstrated high efficacy in several NLP tasks, especially in few-shot settings. Despite …
demonstrated high efficacy in several NLP tasks, especially in few-shot settings. Despite …
Chinese engineering geological named entity recognition by fusing multi-features and data enhancement using deep learning
The engineering geology report serves as a comprehensive portrayal of the geological
conditions and information within a surveyed region, making it highly valuable for extracting …
conditions and information within a surveyed region, making it highly valuable for extracting …
Managing multi-granular probabilistic linguistic information in large-scale group decision making: A personalized individual semantics-based consensus model
Y Liu, Y Yang, L Sun, A Huang - Expert Systems with Applications, 2023 - Elsevier
The multi-granular probabilistic linguistic modeling allows decision makers to express
cognitive information using multiple linguistic term sets based on their preferences …
cognitive information using multiple linguistic term sets based on their preferences …
Learning to summarize Chinese radiology findings with a pre-trained encoder
Automatic radiology report summarization has been an attractive research problem towards
computer-aided diagnosis to alleviate physicians' workload in recent years. However …
computer-aided diagnosis to alleviate physicians' workload in recent years. However …
Clean-label backdoor attack and defense: An examination of language model vulnerability
Prompt-based learning, a paradigm that creates a bridge between pre-training and fine-
tuning stages, has proven to be highly effective concerning various NLP tasks, particularly in …
tuning stages, has proven to be highly effective concerning various NLP tasks, particularly in …
BSD: A multi-task framework for pulmonary disease classification using deep learning
S Yi, S Qin, F She, D Shao - Expert Systems with Applications, 2025 - Elsevier
The diagnosis of pulmonary diseases using deep learning on chest X-ray images can be
affected by the bone structures, the tissue in regions outside the lungs, and the …
affected by the bone structures, the tissue in regions outside the lungs, and the …
Tabular deep learning: a comparative study applied to multi-task genome-wide prediction
Y Fan, P Waldmann - BMC bioinformatics, 2024 - Springer
Purpose More accurate prediction of phenotype traits can increase the success of genomic
selection in both plant and animal breeding studies and provide more reliable disease risk …
selection in both plant and animal breeding studies and provide more reliable disease risk …