Supervised Fine-Tuning
Supervised fine-tuning (SFT) is a method used in machine learning to improve the performance of a pre-trained model. The model is initially trained on a large dataset, then fine-tuned on a smaller, specific dataset. This allows the model to maintain the general knowledge learned from the large dataset while adapting to the specific characteristics of the smaller dataset.
Areas of application
- Image Recognition and Analysis
- Natural Language Processing
- Audio and Speech Recognition
- Autonomous Vehicles
- Medical Diagnosis Systems
- Robotics
- Video Surveillance Systems
- Forecasting and Predictive Analytics
Example
For instance, a pre-trained language model can be fine-tuned on a dataset of legal documents to improve its performance in legal text classification.