An Easy-to-use Framework to Edit Large Language Models.

Overview • Installation • How To Use • Online Tutorial • Contributors

🔔News

• 2023-7-12 We release version 0.0.1, supporting several model editing techniques for LLMs. EasyEdit helps to better align LLMs with changing needs and values of users.
• 2023-5-22 We release the paper "Editing Large Language Models: Problems, Methods, and Opportunities" and provide a paper list at PaperList.
• 2023-3-25 The EasyEdit project has been launched and is under development.

---

Model Editing

Task Definition

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

Model editing aims to adjust an initial base model's $(f_\theta)$ behavior on the particular edit descriptor $[x_e, y_e]$ efficiently, such as(The president of USA: Donald Trump -> Joe Biden):

• $x_e$: "Who is the president of the US?
• $y_e$: "Joe Biden."

without influencing the model behavior on unrelated samples. The ultimate goal is to create an edited model $(f_\theta')$.

Evaluation

The model 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(as below formula).

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

In addition to this, the performance of model editing should be measured from multiple dimensions:

• Reliability: the success rate of editing with a given editing description
• 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 factual reasoning(one hop, synonym, one-to-one relation)
• Efficiency: time and memory consumption required during the editing process

🌟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 Model Editing scenario comprises of three components:

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

• The current supported model editing techniques are as follows:

  • FT-L: Fine-Tuning with $L_\infty$ constraint
  • SERAC: Mitchell et al. Memory-based
  • IKE: Ce Zheng et al. In-Context Editing
  • MEND: Mitchell et al. Hypernetwork
  • KN: Damai Dai et al. Locate then Edit
  • ROME: Kevin Meng et al. Locate and Edit
  • MEMIT: Kevin Meng et al. Locate and Edit

  Due to the limited compatibility of this toolkit and limited by the transformer version, some model editing methods are not supported. You can find relevant editing methods in the following links

  • T-Patcher | KE | CaliNet

Current Implementation

You can choose different editing methods according to your specific needs.

Method	T5	GPT-2	GPT-J	GPT-NEO	LlaMA
FT-L	✅	✅	✅	✅	✅
SERAC	✅	✅	✅
IKE	✅	✅	✅	✅	✅
MEND	✅	✅	✅	✅	✅
KN	✅	✅	✅
ROME		✅	✅	✅	✅
MEMIT		✅	✅	✅

---

🔧Installation

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

git clone https://github.com/zjunlp/EasyEdit.git
conda create -n EasyEdit python=3.9.7
...
pip install -r requirements.txt

📌Use EasyEdit

• edit large language models(LLMs) around 5 seconds

BaseEditor

BaseEditoris the class for Language Modality Model 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, set the corresponding model_name to select the object for model editing.

model_name: gpt2-xl
model_class: GPT2LMHeadModel
tokenizer_class: GPT2Tokenizer
tokenizer_name: gpt2-xl

Step2: Choose the appropriate Model Editing Method The selection of editing methods is a crucial step, as different methods have their own strengths and weaknesses. Users need to consider the trade-off between editing success rate, generalization, and maintaining unrelated performance. For specific performance details of each method, please refer to the paper: Editing Large Language Models: Problems, Methods, and Opportunities.

## 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.

metrics, edited_model, _ = editor.edit(
    prompts=prompts,
    ground_truth=ground_truth,
    target_new=target_new,
    locality_inputs=locality_inputs,
    keep_original_weight=True
)
## metrics: edit success, rephrase success, locality e.g.
## edited_model: post-edit model

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
)

Step6: Run and Edit Done! We can conduct Run and Evaluation.

trainer.run()

• Run: The CHECKPOINT will be saved to the path RESULTS_DIR(in global.yml).
• 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).

TO DO

In next version, we plan to:

• release a multimodal Editor for LLMs.
• support more editing methods for LlaMA
• model editing for other tasks(except factual editing), like textual knowledge editing, personality editing, etc.

Meanwhile, we will offer long-term maintenance to fix bugs, solve issues and meet new requests. So if you have any problems, please put issues to us.

Citation

Please cite our paper if you use EasyEdit in your work.

@misc{yao2023editing,
      title={Editing Large Language Models: Problems, Methods, and Opportunities}, 
      author={Yunzhi Yao and Peng Wang and Bozhong Tian and Siyuan Cheng and Zhoubo Li and Shumin Deng and Huajun Chen and Ningyu Zhang},
      year={2023},
      eprint={2305.13172},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

🎉Contributors

We thank all the contributors to this project, more contributors are welcome!

🙌 We would like to express our heartfelt gratitude for the contribution of ROME to our project, as we have utilized portions of their source code in our project.