1 repositorio
Tools for measuring how a specific knowledge edit affects unrelated neighboring facts in a model.
Distinct from Recognition Accuracy Evaluation: The candidates focus on SQL, biometric, or workflow accuracy, not the 'locality' of knowledge edits in LLMs.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Knowledge Edit Locality Evaluators. Refine with filters or upvote what's useful.
EasyEdit is a framework and toolkit designed for updating, inserting, or erasing specific factual information within large language models without requiring full retraining. It functions as a parameter modifier and knowledge editing system capable of performing targeted weight updates across diverse model architectures. The project distinguishes itself by supporting both text-based and multimodal model editing, allowing for knowledge updates across image and text modalities. It provides utilities for model steering to adjust personality and reasoning patterns in real time via activation inter
Provides specialized metrics to ensure knowledge edits are local and do not corrupt unrelated information.