Field of Study:

Language Model Adapters are a method of fine-tuning pre-trained language models. Instead of fine-tuning all parameters of the model, only a small set of parameters in added adapter modules are trained. This approach allows for a more efficient adaptation of the model to a specific task, while preserving the original model weights. It also enables multi-task learning and transfer learning, as different adapters can be plugged into the model for different tasks.

Synonyms: