knowledge-editing 开源项目推荐（58 个）

zjunlp /EasyEdit

[ACL 2024]一个易于使用的LLM知识编辑框架。

zjunlp /KnowledgeEditingPapers

Must-read Papers on Knowledge Editing for Large Language Models.

zjunlp /KnowledgeCircuits

[NeurIPS 2024] Knowledge Circuits in Pretrained Transformers

hyintell /awesome-refreshing-llms

EMNLP'23 survey: a curation of awesome papers and resources on refreshing large language models (LLMs) without expensive retraining.

bahjat-kawar /time-diffusion

Official code repo for "Editing Implicit Assumptions in Text-to-Image Diffusion Models"

vbario /sleeping-llm

A language model that forms persistent memories from conversation and maintains them through sleep. MEMIT weight editing + null-space-constrained maintenance.

fulvian /engraft-ngram

ENGRAFT: write facts into an LLM's n-gram (Engram) memory table as a removable overlay: 100 facts in a 9 MB file, no weights touched, verified on llama.cpp GGUF (Qwen3.8-Flash-Next).

zjunlp /DynamicKnowledgeCircuits

[ACL 2025] How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training

zjunlp /unlearn

[ACL 2025] Knowledge Unlearning for Large Language Models

zjunlp /KnowUnDo

[EMNLP 2024] To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models

zjunlp /steer-target-atoms

[ACL 2025] Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms

zjunlp /EasyDetect

[ACL 2024] An Easy-to-use Hallucination Detection Framework for LLMs.

YJiangcm /LTE

[ACL 2024] Learning to Edit: Aligning LLMs with Knowledge Editing

baixianghuang /HalluEditBench

Can Knowledge Editing Really Correct Hallucinations? (ICLR 2025)

zjunlp /ReCode

[AAAI 2026] ReCode: Reinforced Code Knowledge Editing for API Updates

zjunlp /PitfallsKnowledgeEditing

[ICLR 2024] Unveiling the Pitfalls of Knowledge Editing for Large Language Models

baixianghuang /editing-attack

Code and dataset for the paper: "Can Editing LLMs Inject Harm?" [AAAI'26]

zjunlp /OneEdit

OneEdit: A Neural-Symbolic Collaboratively Knowledge Editing System.

zjunlp /CaKE

[EMNLP 2025] Circuit-Aware Editing Enables Generalizable Knowledge Learners

zjunlp /BiasEdit

[TrustNLP@NAACL 2025] BiasEdit: Debiasing Stereotyped Language Models via Model Editing