3 citations · 5 across the 4 of their papers we have counts for
4 papers
LoRA-BAM: Input Filtering for Fine-tuned LLMs via Boxed Abstraction Monitors over LoRA Layers
Changshun Wu, Tianyi Duan, Saddek Bensalem +1
Fine-tuning large language models (LLMs) improves performance on domain-specific tasks but can lead to overfitting, making them unreliable on out-of-distribution (OoD) queries. We…
Active Deep Learning on Entity Resolution by Risk Sampling
Youcef Nafa, Qun Chen, Zhaoqiang Chen +4
While the state-of-the-art performance on entity resolution (ER) has been achieved by deep learning, its effectiveness depends on large quantities of accurately labeled training da…
Adaptive Deep Learning for Entity Resolution by Risk Analysis
Zhaoqiang Chen, Qun Chen, Youcef Nafa +4
The state-of-the-art performance on entity resolution (ER) has been achieved by deep learning. However, deep models are usually trained on large quantities of accurately labeled tr…
Towards Interpretable and Learnable Risk Analysis for Entity Resolution
Zhaoqiang Chen, Qun Chen, Boyi Hou +3
Machine-learning-based entity resolution has been widely studied. However, some entity pairs may be mislabeled by machine learning models and existing studies do not study the risk…