EasyEdit

<div align="center"> <img src="figs/logo.png" width="180px">

---

<p align="center"> <a href="#requirements">Installation</a> • <a href="#use-easyedit">QuickStart</a> • <a href="https://ribbon-muskox-3ac.notion.site/EasyEdit1-0-213e624c1c2680318840d9abbdaa83c5">Doc</a> • <a href="https://arxiv.org/abs/2401.01286">Paper</a> • <a href="https://huggingface.co/spaces/zjunlp/EasyEdit">Demo</a> • <a href="https://huggingface.co/datasets/zjunlp/KnowEdit">Benchmark</a> • <a href="#contributors">Contributors</a> • <a href="https://github.com/zjunlp/EasyEdit/blob/main/tutorial.pdf">Slides</a> • <a href="https://youtu.be/Gm6T0QaaskU", target="_blank">Video</a> • <a href="https://twitter.com/_akhaliq/status/1742371655765164133", target="_blank">Featured By AK</a> </p> </div> <h1 style="font-size: 32px; color: #333; text-align: left;"> <span style="font-size: 30px; color:rgb(180, 148, 61);">⭐</span> Key News </h1> <p align="left"> ✨ <strong><a href="https://ribbon-muskox-3ac.notion.site/EasyEdit1-0-213e624c1c2680318840d9abbdaa83c5" style="text-decoration: none; "> EasyEdit Beginner's Guide </a></strong> officially published! <br> We have written a detailed beginner's guide for EasyEdit, specifically tailored for newcomers to the fields of knowledge editing and model editing. By reading this manual, you can quickly understand and start using EasyEdit.

✨ <strong>EasyEdit blog published!</strong> <br> We have also published a blog post titled "Take Control of What Your LLM Knows and Does — with the EasyEdit Tool Series", where you can learn more about how EasyEdit empowers you to control and edit your LLM’s knowledge and behavior.  

</p> <h1 style="font-size: 32px; color: #333; text-align: left;"> <span style="font-size: 30px; color:rgb(180, 148, 61);">📢</span> Update </h1> <p align="left"> 🔥 <strong><a href="README_2.md" style="text-decoration: none; ">EasyEdit 2.0</a></strong> officially published! <br> Unlike EasyEdit1.0, which achieves knowledge editing by updating internal parameters or introducing additional parameters, EasyEdit2 enables real-time steering of LLMs during inference. It provides a unified framework for controllability without retraining, seamlessly integrating various steering methods for ease of use and evaluation. &nbsp; 👉 <strong><a href="README_2.md" style="text-decoration: none; ">[README]</a></strong> (for more details). </p>

Table of Contents

• Table of Contents
• 🔔News
• Editing Demo
• Knowledge Editing
  • Task Definition
    • Knowledge insert
    • Knowledge update
    • Knowledge erase
  • Comparisons of the different technologies
  • Evaluation
• 🌟Overview
  • Current Implementation
  • Quick Start on Some Works
  • Tutorial notebook
• Requirements
  • 🔧Pip Installation
  • Editing GPU memory usage
• 📌Use EasyEdit
  • BaseEditor
    • Introduction by a Simple Example
  • Evaluation
  • Trainer
• Use EasyEdit with KnowEdit
  • Dataset
  • Usage
• Editing Performance
• Citation
• 🎉Contributors
  • Other Related Projects

🔔News

• 2026-03-04, 🎉 SteerEval is released — a hierarchical benchmark for evaluating LLM controllability across behavioral domains and granularity levels, with an automated data synthesis pipeline.
• 2025-10-12, ⚡ LightMem is released — a lightweight and efficient memory framework empowering LLMs and AI agents with long-term memory capabilities!
• 2025-10-02, 👑 SimIE has arrived — a general framework for lifelong model editing, which restores the strong performance of parameter-modifying methods from standard model editing in a lifelong context!
• 2025-09-10, 🎉🎉 EasyEdit2 Paper has been accepted by the EMNLP 2025 System Demonstration Track.
• 2025-07-24, 🚀🚀the EasyEdit has added three new unstructured long-form knowledge editing datasets AKEW, LEME and UNKE. In addition, EasyEdit also incorporated two of the currently most popular unstructured editing methods UNKE and AnyEdit. EasyEdit2 also supports the representation steering method RePS and provides initial support for AxBench-style evaluation.
• 2025-06-07, 👑 UltraEdit has arrived — powered by a lifelong normalization strategy that continuously updates feature statistics across turns, it can edit 20K samples on a 7B model in just 5 minutes and scales stably to millions !
• 2025-06-05, 🌟🌟the EasyEdit has added a new model editing algorithm CORE, designed to strengthen context robustness by minimizing context-sensitive variance in hidden states of the model for edited knowledge.
• 2025-05-28, 🌟🌟the EasyEdit has added a new model editing algorithm NAMET, which introduces noise during memory extraction via a one-line modification to MEMIT. Thanks to @ybdai7 for contribution!
• 2025-05-15, 🚀🚀We released a new blog Reflection on Knowledge Editing: Charting the Next Steps discussing the next step for knowledge editing research.
• 2025-04-03, 🚀🚀We have upgraded EasyEdit and introduced EasyEdit2! EasyEdit2 provides an easy-to-use steering framework for editing large language models with precision and flexibility. This upgrade enhances the framework’s capabilities, making it more robust and adaptable for various steering methods. More details can be found in our paper, in the README and on our website.

<details> <summary><b>Previous News</b></summary>

• 2025-03-04, 🌟🌟In addition to the original token-level teacher-forcing paradigm for evaluation, EasyEdit has integrated a new evaluation method, following the paper titled "The Mirage of Model Editing: Revisiting Evaluation in the Wild". You can use this script to quickly launch this evaluation approach, which better aligns with real-world requirements. Special thanks to @WanliYoung for contribution!

• 2025-01-03, We have updated the evaluation method in paper "CKnowEdit: A New Chinese Knowledge Editing Dataset for Linguistics, Facts, and Logic Error Correction in LLMs", adopting an LLM-as-a-judge approach that is more aligned with real-world scenarios and practical applications. Both the experimental results and the running scripts have been updated accordingly in readme.

• 2024-11-19, we update the Table 4 results in the paper "A Comprehensive Study of Knowledge Editing for Large Language Models" after optimizing certain methods (related to AdaLoRA) and fixing computational bugs (related to ROME and MEMIT) in the EasyEdit (More details in https://github.com/zjunlp/EasyEdit/issues/427). These improvements have led to better results than before. We will continue updating this paper and welcome everyone to discuss and exchange ideas.

• 2024-11-11, 🎉🎉the paper on model editing for LLMs4Code, "Model Editing for LLMs4Code: How Far are We?", has been accepted by ICSE 2025! This work proposes a benchmark for LLMs4Code editing, CLMEEval, which is built upon EasyEdit!

• 2024-11-09, we fixed a bug regarding the KnowEdit results in the https://github.com/zjunlp/EasyEdit/issues/390. Thanks for the help of @StarLooo to help us with it.

• 2024-10-24, EasyEdit has added two new knowledge editing methods, AlphaEdit. In addition, we have fixed several bugs.

• 2024-10-23, the EasyEdit integrates constrained decoding methods from steering editing to mitigate hallucination in LLM and MLLM, with detailed information available in DoLa and DeCo.

• 2024-09-26, 🎉🎉 our paper "WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Models" has been accepted by NeurIPS 2024.

• 2024-09-20, 🎉🎉 our papers: "[Knowledge Mechanisms in Large Language Models: A Su