[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.

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

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

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

[NeurIPS 2024] Knowledge Circuits in Pretrained Transformers

Code for "Learning to Edit: Aligning LLMs with Knowledge Editing (ACL 2024)"

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

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

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

OneEdit: A Neural-Symbolic Collaboratively Knowledge Editing System.

Code and dataset for the paper: "Can Editing LLMs Inject Harm?"

Official codes for COLING 2024 paper "Robust and Scalable Model Editing for Large Language Models": https://arxiv.org/abs/2403.17431v1

Stable Knowledge Editing in Large Language Models

Official implementation for Zhong & Le et al., GNNs Also Deserve Editing, and They Need It More Than Once. ICML 2024

Can Knowledge Editing Really Correct Hallucinations?

Debiasing Stereotyped Language Models via Model Editing

MLaKE: Multilingual Knowledge Editing Benchmark for Large Language Models

An Automated Framework to Construct Datasets for Assessing Knowledge Editing or Multi-Hop Reasoning Capability of Language Models.