EasyEdit

---

Installation • QuickStart • Doc • Paper • Demo • Benchmark • Contributors • Slides • Video • Featured By AK

⭐ Key News

✨ EasyEdit Beginner's Guide officially published!
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.

✨ EasyEdit blog published!
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.  

📢 Update

🔥 EasyEdit 2.0 officially published!
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.   👉 [README] (for more details).

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
  • ⚡uv 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

• 2026-07-13, 🎉 EasyEdit has been selected for the CCF ODTC open source incentive program.
• 2026-07-08, 🚀 EasyEdit has received a major upgrade, bringing Transformers 5.x compatibility, new models support, more reliable multi-GPU editing, enhanced multimodal pipelines, a unified EasyEdit2 steering workflow, expanded vLLM support, and faster multi-worker deployment.
• 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.

A Comprehensive Study of Knowledge Editing for Large Language Models [paper][benchmark][code]

IJCAI 2024 Tutorial Google Drive

COLING 2024 Tutorial Google Drive

AAAI 2024 Tutorial Google Drive

AACL 2023 Tutorial [Google Drive] [Baidu Pan]

Editing Demo

There is a demonstration of editing. The GIF file is created by Terminalizer.

We provide a handy Jupyter Notebook! It allows you to edit a LLM’s knowledge of the US president, switching from Biden to Trump and even back to Biden. This includes methods like WISE, AlphaEdit, AdaLoRA, and Prompt-based editing.

Knowledge Editing

Task Definition

Deployed models may still make unpredictable errors. For example, LLMs notoriously hallucinate, perpetuate bias, and factually decay, so we should be able to adjust specific behaviors of pre-trained models.

Knowledge editing aims to adjust base model’s $(f_\theta)$ behavior on the particular edit descriptor $[x_e, y_e]$​​​ efficiently.

Multi Setting

Single Knowledge Editing

Evaluating the performance of the model after a single edit. The model reloads the original weights (e.g. LoRA discards the adapter weights) after a single edit. You should set sequential_edit=False

$$\theta’ \leftarrow \text{arg} \min\limits_{\theta} (\Vert f_\theta(x_e) - y_e \Vert)$$

Continuous Knowledge Editing

This requires sequentially editing, and evaluation is performed after all knowledge updates have been applied:

$$\theta’ \leftarrow \text{arg} \min\limits_{\theta} \sum_{e=1}^{\Vert X_e \Vert} (\Vert f_\theta(x_e) - y_e \Vert)$$

It makes parameter adjustments for $(x_e, y_e)$, where $x_e \in X_e$ and $f_\theta’(x_e) = y_e$. Here, $X_e$​ represents the whole edit set. To enable continuous editing, you can set sequential_edit=True: README (for more details).

Multi Scenario

Comparisons of different technologies

Evaluation

The knowledge editing process generally impacts the predictions for a broad set of inputs that are closely associated with the edit example, called the editing scope.

A successful edit should adjust the model’s behavior within the editing scope while remaining unrelated inputs:

$$ f_{\theta_{e}}(x) = \begin{cases} y_e & \text{if } x \in I(x_e,y_e) \ f_{\theta}(x) & \text{if } x \in O(x_e, y_e) \end{cases} $$

• Reliability: the success rate of editing with a given editing descriptor
• Generalization: the success rate of editing within the editing scope
• Locality: whether the model’s output changes after editing for unrelated inputs
• Portability: the success rate of editing for reasoning/application(one hop, synonym, logical generalization)
• Efficiency: time and memory consumption

🌟Overview

EasyEdit is a Python package for edit Large Language Models (LLM) like GPT-J, Llama, GPT-NEO, GPT2, T5(support models from 1B to 65B), the objective of which is to alter the behavior of LLMs efficiently within a specific domain without negatively impacting performance across other inputs. It is designed to be easy to use and easy to extend.

• EasyEdit contains a unified framework for Editor, Method and Evaluate, respectively representing the editing scenario, editing technique, and evaluation method.

• Each Knowledge Editing scenario comprises of three components:

  • Editor: such as BaseEditor(Factual Knowledge and Generation Editor) for LM, MultiModalEditor(MultiModal Knowledge).
  • Method: the specific knowledge editing technique used(such as ROME, MEND, …).
  • Evaluate: Metrics for evaluating knowledge editing performance.
    • Reliability, Generalization, Locality, Portability

• The current supported knowledge editing techniques are as follows:

  • Memory-based: SERAC, IKE, GRACE, MELO, WISE
  • Meta-learning: MEND, InstructEdit, MALMEN
  • Locate-then-edit: KN, ROME, MEMIT, PMET, DINM, R-ROME, EMMET
  • FT-L

  Note 1: Due to the limited compatibility of this toolkit, some knowledge editing methods including T-Patcher, KE, CaliNet are not supported.

  Note 2: Similarly, the MALMEN method is only partially supported due to the same reasons and will continue to be improved.

Current Implementation

You can choose different editing methods according to your specific needs. GPT series includes GPT-2, GPT-J and GPT-NEO.

❗️❗️ If you intend to use Mistral, please update the transformers library to version 4.34.0 manually. You can use the following code: pip install transformers==4.34.0.

We also support some knowledge editing methods for LMMs (Large Multimodal Models). Please refer to MultimodalEdit.md for more details.

Quick Start on Some Works

Dataset

Benchmark: KnowEdit [Hugging Face][WiseModel][ModelScope]

❗️❗️ To be noted, KnowEdit is constructed by re-organizing and extending existing datasests including WikiBio, ZsRE, WikiData_Counterfact, WikiData_Recent, convsent, Sanitation to make a comprehensive evaluation for knowledge editing. Special thanks to the builders and maintainers of the those datasets.

Please note that Counterfact and WikiData_Counterfact are not the same dataset.

We provide detailed scripts for user to easily use KnowEdit, please refer to examples.

knowedit
├── WikiBio
│   ├── wikibio-test-all.json
│   └── wikibio-train-all.json
├── ZsRE
│   └── ZsRE-test-all.json
├── wiki_counterfact
│   ├── test_cf.json
│   └── train_cf.json
├── convsent
│   ├── blender_test.json
│   ├── blender_train.json
│   └── blender_val.json
├── convsent
│   ├── trivia_qa_test.json
│   └── trivia_qa_train.json
└── wiki_recent
    ├── recent_test.json
    └── recent_train.json

Datasets for Chinese Knowledge: CKnowEdit

• Here, you can follow CKnowEdit.md to find more details about CKnowEdit and run Chinese knowledge editing experiments.

"prompt": query inputed to the model (str)
"target_old": the incorrect response previously generated by the model (str)
"target_new": the accurate answer of the prompt (str)
"portability_prompt": new prompts related to the target knowledge (list or None)
"portability_answer": accurate answers corresponding to the portability_prompt (list or None)
"locality_prompt": new prompts unrelated to the target knowledge (list or None)
"locality_answer": accurate answers corresponding to the locality_prompt (list or None)
"rephrase": alternative ways to phrase the original prompt (list)

CknowEdit
├── Chinese Literary Knowledge
│   ├── Ancient Poetry
│   ├── Proverbs
│   └── Idioms
├── Chinese Linguistic Knowledge
│   ├── Phonetic Notation
│   └── Classical Chinese
├── Chinese Geographical Knowledge
└── Ruozhiba

Datasets for Factual Knowledge

We provide zsre and counterfact datasets to verify the effectiveness of knowledge editing. You can download them here. [Google Drive], [BaiduNetDisk].

• For locality, in addition to testing unrelated instances, we also provide tests on distracting (reference: Detecting Edit Failures…), other attribution, and other downstream tasks (such as commonsense reasoning).
• For portability, it tests whether the model can apply edited instances for inference. We provide evaluations for one-hop reasoning, subject alias, and inverse relation (eg, a one-to-one relationship between spouses should be bidirectionally edited).

editing-data
├── counterfact
│   ├── counterfact-edit.json
│   ├── counterfact-train.json
│   └── counterfact-val.json
├── locality
│   ├── Commonsense Task
│   │   ├── piqa_valid-labels.lst
│   │   └── piqa_valid.jsonl
│   ├── Distracting Neighbor
│   │   └── counterfact_distracting_neighbor.json
│   └── Other Attribution
│       └── counterfact_other_attribution.json
├── portability
│   ├── Inverse Relation
│   │   └── zsre_inverse_relation.json
│   ├── One Hop
│   │   ├── counterfact_portability_gpt4.json
│   │   └── zsre_mend_eval_portability_gpt4.json
│   └── Subject Replace
│       ├── counterfact_subject_replace.json
│       └── zsre_subject_replace.json
└── zsre
    ├── zsre_mend_eval.json
    ├── zsre_mend_train_10000.json
    └── zsre_mend_train.json

Datasets for Conceptual Knowledge: ConceptEdit

• Here, you can follow ConceptEdit.md to run concept editing experiments.

data
└──concept_data.json
    ├──final_gpt2_inter.json
    ├──final_gpt2_intra.json
    ├──final_gptj_inter.json
    ├──final_gptj_intra.json
    ├──final_llama2chat_inter.json
    ├──final_llama2chat_intra.json
    ├──final_mistral_inter.json
    └──final_mistral_intra.json

Datasets for Multimodal Knowledge: MMEdit

• All images used in E-IC and E-VQA are available for download at Google Drive
• For locality, it is the same as factual editing in order to measure whether unrelated facts retain their outputs.
• For multimodal locality, it assesses the impact of editing on the visual module, which is similar to regular locality.
• The details of the impact of editing on other in-domain samples are in ComprehendEdit.

editing-data
├── caption
│   ├── caption_train_edit.json
│   └── caption_eval_edit.json
├── locality
│   ├── NQ dataset
│   │   ├── train.json
│   │   └── validation.json
├── multimodal_locality
│   ├── OK-VQA dataset
│   │   ├── okvqa_loc.json
└── vqa
    ├── vqa_train.json
    └── vqa_eval.json

Datasets for detoxifying LLMs: SafeEdit

• Here, you can follow SafeEdit.md to run detoxification editing experiments.

data
└──SafeEdit_train.json
└──SafeEdit_val.json
└──SafeEdit_test.json
    

Tutorial notebook

Datasets for Real-World Lifelong Knowledge Editing: WikiBigEdit

• Here, you can follow run_WikiBigEdit.py to run WikiBigEdit edits using EasyEdit.

• If you want to learn more about WikiBigEdit, please refer to the following paper: Understanding the Limits of Lifelong Knowledge Editing in LLMs

Requirements

🔧Pip Installation

Note: Please use Python 3.9+ for EasyEdit To get started with pip, simply install conda and run:

git clone https://github.com/zjunlp/EasyEdit.git
cd EasyEdit
conda create -n EasyEdit python=3.10
conda activate EasyEdit
pip install -r requirements.txt

⚡uv Installation

You can also use uv for faster dependency installation:

git clone https://github.com/zjunlp/EasyEdit.git
cd EasyEdit
conda create -n EasyEdit python=3.10
conda activate EasyEdit
pip install uv
uv pip install --torch-backend cu128 -r requirements.txt

If you are installing for a CPU-only environment, replace the last command with:

uv pip install --torch-backend cpu -r requirements.txt

After installation, you can verify the environment with:

uv pip check

Editing GPU memory usage

Our results are all based on the default configuration

📌Use EasyEdit

• Edit large language models(LLMs) around 5 seconds

• Following example shows you how to perform editing with EasyEdit. More examples and tutorials can be found at examples

BaseEditor

BaseEditoris the class for Language Modality Knowledge Editing. You can choose the appropriate editing method based on your specific needs.

• Due to different transformer versions and different GPU models, the editing results may fluctuate slightly.

Introduction by a Simple Example

With the modularity and flexibility of EasyEdit, you can easily use it to edit model.

Step1: Define a PLM as the object to be edited. Choose the PLM to be edited. EasyEdit supports partial models(T5, GPTJ, GPT-NEO, LlaMA so far) retrievable on HuggingFace. The corresponding configuration file directory is hparams/YUOR_METHOD/YOUR_MODEL.YAML, such as hparams/MEND/gpt2-xl.yaml, set the corresponding model_name to select the object for knowledge editing.

model_name: gpt2-xl
model_class: GPT2LMHeadModel
tokenizer_class: GPT2Tokenizer
tokenizer_name: gpt2-xl
model_parallel: false # true for multi-GPU editing

Step2: Choose the appropriate Knowledge Editing Method

## In this case, we use MEND method, so you should import `MENDHyperParams`
from easyeditor import MENDHyperParams
## Loading config from hparams/MEMIT/gpt2-xl.yaml
hparams = MENDHyperParams.from_hparams('./hparams/MEND/gpt2-xl')

Step3: Provide the edit descriptor and edit target

## edit descriptor: prompt that you want to edit
prompts = [
    'What university did Watts Humphrey attend?',
    'Which family does Ramalinaceae belong to',
    'What role does Denny Herzig play in football?'
]
## You can set `ground_truth` to None !!!(or set to original output)
ground_truth = ['Illinois Institute of Technology', 'Lecanorales', 'defender']
## edit target: expected output
target_new = ['University of Michigan', 'Lamiinae', 'winger']

Step4: Combine them into a BaseEditor EasyEdit provides a simple and unified way to init Editor, like huggingface: from_hparams.

## Construct Language Model Editor
editor = BaseEditor.from_hparams(hparams)

Step5: Provide the data for evaluation Note that the data for portability and locality are both optional(set to None for basic editing success rate evaluation only). The data format for both is a dict, for each measurement dimension, you need to provide the corresponding prompt and its corresponding ground truth. Here is an example of the data:

locality_inputs = {
    'neighborhood':{
        'prompt': ['Joseph Fischhof, the', 'Larry Bird is a professional', 'In Forssa, they understand'],
        'ground_truth': ['piano', 'basketball', 'Finnish']
    },
    'distracting': {
        'prompt': ['Ray Charles, the violin Hauschka plays the instrument', 'Grant Hill is a professional soccer Magic Johnson is a professional', 'The law in Ikaalinen declares the language Swedish In Loviisa, the language spoken is'],
        'ground_truth': ['piano', 'basketball', 'Finnish']
    }
}

In the above example, we evaluate the performance of the editing methods about “neighborhood” and “distracting”.

Step6: Edit and Evaluation Done! We can conduct Edit and Evaluation for your model to be edited. The edit function will return a series of metrics related to the editing process as well as the modified model weights. [sequential_edit=True for continuous editing]

metrics, edited_model, _ = editor.edit(
    prompts=prompts,
    ground_truth=ground_truth,
    target_new=target_new,
    locality_inputs=locality_inputs,
    sequential_edit=False # True: start continuous editing ✈️
)
## metrics: edit success, rephrase success, locality e.g.
## edited_model: post-edit model

The maximum input length for EasyEdit is 512. If this length is exceeded, you will encounter the error “CUDA error: device-side assert triggered.” You can modify the maximum length in the following file:LINK

Step7: RollBack In sequential editing, if you are not satisfied with the outcome of one of your edits and you do not wish to lose your previous edits, you can use the rollback feature to undo your previous edit. Currently, we only support the GRACE method. All you need to do is a single line of code, using the edit_key to revert your edit.

editor.rolllback('edit_key')

In EasyEdit, we default to using target_new as the edit_key

Evaluation

We specify the return metrics as dict format, including model prediction evaluations before and after editing. For each edit, it will include the following metrics:

• rewrite_acc $\rightarrow$ Reliablilty
• rephrase_acc $\rightarrow$ Generalization
• locality $\rightarrow$ Locality
• portablility $\rightarrow$ Portablility

{
    "post": {
        "rewrite_acc": ,
        "rephrase_acc": ,
        "locality": {
            "YOUR_LOCALITY_KEY": ,
            //...
        },
        "portablility": {
            "YOUR_PORTABILITY_KEY": ,
            //...
        },
    },
    "pre": {
        "rewrite_acc": ,
        "rephrase_acc": ,
        "portablility": {
            "YOUR_PORTABILITY_KEY": ,
            //...
        },
    }
}

• For evaluation for Reliablilty, you only need to provide the corresponding editing prompts and editing target_new.
• For evaluation for Generalization, rephrase_prompts are required.
• For evaluation for Locality and Portablility, you need to define the name of the corresponding metric, as well as prompts and ground_truth.

  • Note: the length needs to be equal to the edit prompts

Trainer

• meta-learning based: MEND
• memory-based routing: SERAC

For above editing methods, pre-training of corresponding meta-networks or classifiers is required. Therefore, in EasyEdit, we provide a unified framework for pretraining the relevant network structures. Take the training MEND for example:

• Step 1 and Step 2 are the same as the example above, which involves selecting the appropriate editing model and editing method.

Step3: Provide the edit training set The currently supported and available datasets are: zsre and counterfact(Google Drive). Please place them in the “data” directory and initialize the dataset_class (ZsreDataset for zsre and CounterFactDataset for counterfact) to load the corresponding training set.

train_ds = ZsreDataset('./data/zsre_mend_train.json', config=training_hparams)
eval_ds = ZsreDataset('./data/zsre_mend_eval.json', config=training_hparams)

Step4: Combine them into a Trainer

trainer = EditTrainer(
    config=training_hparams,
    train_set=train_ds,
    val_set=eval_ds
)

Step5: Run and Edit Done! We can conduct Run and Evaluation.

trainer.run()

• Run: The CHECKPOINT will be saved to the path results_dir.
• Edit: Set the archive field in the hparams file to CHECKPOINT. EasyEdit will automatically load the corresponding pre-trained weights during the editing process(Go to edit).

Training Example

from easyeditor import EditTrainer, MENDTrainingHparams, ZsreDataset

training_hparams = MENDTrainingHparams.from_hparams('hparams/TRAINING/MEND/llama-7b.yaml')
train_ds = ZsreDataset('./data/zsre/zsre_mend_train.json', config=training_hparams)
eval_ds = ZsreDataset('./data/zsre/zsre_mend_eval.json', config=training_hparams)
trainer = EditTrainer(
    config=training_hparams,
    train_set=train_ds,
    val_set=eval_ds
)
trainer.run()

Use EasyEdit with KnowEdit

Dataset

KnowEdit is a benchmark dataset of knowledge editing for LLMs. You can easily obtain KnowEdit from HuggingFace, HuggingFace, and ModelScope.

Usage

We provide detailed scripts for user to easily use KnowEdit, please refer to examples.

Editing Performance

We present editing results of the four metrics on LlaMA-2-7B using EasyEdit. We adopt ZsRE as the test dataset.

❗️❗️Editing llama-2-7B requires 40G+ VRAM on GPU. (OOM solution)

We also present editing results of KnowEdit on LlaMA-2-7B using EasyEdit.

README 内容过长，已截取前 64 KB。完整内容请前往 GitHub 仓库查看。