jianghoucheng/AnyEdit
AnyEdit: Edit Any Knowledge Encoded in Language Models, ICML 2025
AnyEdit helps developers precisely update specific information within large language models (LLMs) without retraining the entire model. You provide the LLM and the knowledge you want to change, and AnyEdit updates that knowledge consistently across various formats. This tool is for AI engineers and researchers working with LLMs who need to modify factual information or model behaviors efficiently.
Use this if you are an AI developer who needs to update or correct specific long-form knowledge in an existing large language model.
Not ideal if you are a non-developer seeking a user-friendly interface to make simple edits to an LLM, or if you want to fine-tune an LLM for entirely new tasks rather than edit existing knowledge.
Stars
46
Forks
6
Language
Python
License
MIT
Category
Last pushed
Nov 06, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/jianghoucheng/AnyEdit"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
steering-vectors/steering-vectors
Steering vectors for transformer language models in Pytorch / Huggingface
jianghoucheng/AlphaEdit
AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models, ICLR 2025 (Outstanding Paper)
kmeng01/memit
Mass-editing thousands of facts into a transformer memory (ICLR 2023)
boyiwei/alignment-attribution-code
[ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
zjunlp/KnowledgeCircuits
[NeurIPS 2024] Knowledge Circuits in Pretrained Transformers