EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Models
Large Language Models (LLMs) usually suffer from knowledge cutoff or fallacy issues, which means they are unaware of unseen events or generate text with incorrect fact...
Tags：Paper and LLMsKnowledge Editing FrameworkPricing Type
- Pricing Type: Free
- Price Range Start($):
GitHub Link
The GitHub link is https://github.com/zjunlp/easyedit
Introduce
“EasyEdit” is an accessible knowledge editing framework for Large Language Models (LLMs) such as GPT-J, GPT-NEO, and more. The framework’s purpose is to adjust LLM behaviors while maintaining their performance across various inputs. It involves a modular system with Editors, Methods, and Evaluations. Notably, it supports various knowledge editing techniques like FT-L, SERAC, MEND, and ROME, focusing on reliability, generalization, locality, portability, and efficiency. The project, publicly open-sourced, includes installation instructions, usage examples, and evaluation results for editing LLMs effectively.”
Content
EasyEdit is a Python package for edit Large Language Models (LLM) like GPT-J, Llama, GPT-NEO, GPT2, T5(support models from 1B to 65B), the objective of which is to alter the behavior of LLMs efficiently within a specific domain without negatively impacting performance across other inputs. It is designed to be easy to use and easy to extend.
Large Language Models (LLMs) usually suffer from knowledge cutoff or fallacy issues, which means they are unaware of unseen events or generate text with incorrect facts owing to the outdated/noisy data.
Related
MS3D++ provides a straightforward approach to domain adaptation by generating high-quality pseudo-labels, enabling the adaptation of 3D detectors to a diverse range of lidar types, regardless of their density.
