MIT, Northeastern & Technion Propose ROME for Efficient Locating and Editing of Factual Associations in GPT Models

In the new paper Locating and Editing Factual Associations in GPT, a research team from MIT CSAIL, Northeastern University and Technion IIT examines how information flows during knowledge recall in large autoregressive transformers and introduces Rank-One Model Editing (ROME), a simple, zero-shot principled model editor capable of locating and editing factual associations in such models.

ai artificial intelligence deep-neural-networks gpt language model machine learning machine learning & data science mit ml nature language tech popular research technion technology