LLM Knowledge Editing LLM Tools

Tools and methods for modifying, updating, and correcting factual knowledge encoded in large language models after training. Includes techniques for targeted fact editing, knowledge localization, and preserving model behavior during edits. Does NOT include general fine-tuning, RAG systems, or prompt engineering approaches.

There are 15 llm knowledge editing tools tracked. The highest-rated is zjunlp/KnowledgeEditingPapers at 44/100 with 1,219 stars.

Get all 15 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=llm-tools&subcategory=llm-knowledge-editing&limit=20"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

#	Tool	Score	Tier	Stars	Language
1	zjunlp/KnowledgeEditingPapers Must-read Papers on Knowledge Editing for Large Language Models.	44	Emerging	1,219	—
2	zjunlp/unlearn [ACL 2025] Knowledge Unlearning for Large Language Models	39	Emerging	48	Python
3	OFA-Sys/Ditto A self-ailgnment method for role-play. Benchmark for role-play. Resources...	39	Emerging	211	Jupyter Notebook
4	zjunlp/CaKE [EMNLP 2025] Circuit-Aware Editing Enables Generalizable Knowledge Learners	33	Emerging	19	Python
5	taco-group/Re-Align [EMNLP'25] A novel alignment framework that leverages image retrieval to...	31	Emerging	50	Python
6	zjunlp/AutoSteer [EMNLP 2025] AutoSteer: Automating Steering for Safe Multimodal Large Language Models	30	Emerging	13	Python
7	zjunlp/steer-target-atoms [ACL 2025] Beyond Prompt Engineering: Robust Behavior Control in LLMs via...	30	Emerging	37	Python
8	zjunlp/KnowUnDo [EMNLP 2024] To Forget or Not? Towards Practical Knowledge Unlearning for...	27	Experimental	47	Python
9	MaxBelitsky/cache-steering KV Cache Steering for Inducing Reasoning in Small Language Models	27	Experimental	46	Python
10	VinAIResearch/HPR Householder Pseudo-Rotation: A Novel Approach to Activation Editing in LLMs...	26	Experimental	7	Python
11	zjunlp/PitfallsKnowledgeEditing [ICLR 2024] Unveiling the Pitfalls of Knowledge Editing for Large Language Models	23	Experimental	22	Python
12	Hi-archers/MLaKE COLING 2025: MLaKE: Multilingual Knowledge Editing Benchmark for Large...	17	Experimental	5	—
13	G-Art/matrix_steering_vector_research Iterative Sparse Matrix Steering: Closed-Form Subspace Alignment for...	17	Experimental	2	Jupyter Notebook
14	Luca-vdB/activation-steering A minimalistic implementation of Activation Steering, an optimization free...	16	Experimental	2	Jupyter Notebook
15	ekonwang/UAL4Alignment Uncertainty Aware Learning for Language Model Alignment (Proceedings of the...	11	Experimental	2	Python

Comparisons in this category

unlearn and KnowUnDo (39 vs 27)