作者位次 #5/10ACL 2026Workshop· Natural Language Processing
LLM s for Now, Fine-Tuning for Later: An Ensemble Approach to Data Drift in Domain-Specific Tasks
Yuxuan Lu · Bingsheng Yao · Shao Zhang · Yisi Sang · Yun Wang · Hansu Gu · Peng Zhang · Tun Lu · Toby Jia-Jun Li · Dakuo Wang
摘要
Deploying machine learning models in real-world domain-specific scenarios is challenged by the scarcity of expert annotations and by data drift, where the statistical properties of incoming data continuously evolve. Active Learning (AL) iteratively improves compact models with expert annotations...