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

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

AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models, ICLR 2025 (Outstanding Paper)

[NeurIPS 2024] Knowledge Circuits in Pretrained Transformers

Decomposing and Editing Predictions by Modeling Model Computation

AdaMerging: Adaptive Model Merging for Multi-Task Learning. ICLR, 2024.

Practical Continual Forgetting for Pre-trained Vision Models (CVPR 2024; T-PAMI 2026)

Representation Surgery for Multi-Task Model Merging. ICML, 2024.

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

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

AnyEdit: Edit Any Knowledge Encoded in Language Models, ICML 2025

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

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

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

Dataset for Unified Editing, EMNLP 2023. This is a model editing dataset where edits are natural language phrases.

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

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

OneEdit: A Neural-Symbolic Collaboratively Knowledge Editing System.

[AAAI 2025 oral] Attribution Analysis Meets Model Editing: Advancing Knowledge Correction in Vision Language Models with VisEdit

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

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

Official repository for Targeted Unlearning with Single Layer Unlearning Gradient (SLUG), ICML 2025

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

Neuron-Level Sequential Editing for Large Language Models, ACL 2025 Main

GNNs Also Deserve Editing, and They Need It More Than Once. ICML 2024

A list of awesome resources related to constraint learning

Federated Learning Project for Machine Learning and Deep Learning course at Politecnico di Torino

A Terminal Editor, with model editing, window spliting, and tree-sitter based code highlighting. More features are being developed!

Source Code of "Fine-tuning Done Right in Model Editing"

[NeurIPS 2025 B & D] UniEdit: A Unified Knowledge Editing Benchmark for Large Language Models