all AI news
FTFT: Efficient and Robust Fine-Tuning by Transferring Training Dynamics
April 2, 2024, 7:45 p.m. | Yupei Du, Albert Gatt, Dong Nguyen
cs.LG updates on arXiv.org arxiv.org
Abstract: Despite the massive success of fine-tuning Pre-trained Language Models (PLMs), they remain susceptible to out-of-distribution input. Dataset cartography is a simple yet effective dual-model approach that improves the robustness of fine-tuned PLMs. It involves fine-tuning a model on the original training set (i.e. reference model), selecting a subset of important training instances based on the training dynamics, and fine-tuning again only on these selected examples (i.e. main model). However, this approach requires fine-tuning the same …
abstract arxiv cs.cl cs.lg dataset distribution dynamics fine-tuning language language models massive reference robust robustness set simple success training type
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Senior Data Scientist
@ ITE Management | New York City, United States