Subject
3 entries
Model Editing
Bookmarks
Editing Models with Task Arithmetic
Task Arithmetic shows that fine-tuning deltas (task vectors) can be added, subtracted, and combined arithmetically to edit model behavior — without any additional training. Negation forgets a task; addition combines capabilities; analogical transfer works across tasks.
Memory-Based Model Editing at Scale
ICML 2022 paper on memory-based model editing at scale — a method for locally updating a neural network's factual knowledge without full retraining. Uses a cache of explicit edits that override the base model's predictions for targeted inputs.
Editable Neural Networks
ICLR paper proposing 'editable neural networks' — a method for making targeted modifications to a model's behavior on specific inputs without disrupting performance elsewhere. An early formalization of the model editing problem.