Skip to content

This is the code repo for our paper "Enhancing Knowledge Integration and Utilization of Large Language Models via Constructivist Cognition Modeling".

License

Notifications You must be signed in to change notification settings

OpenMatch/ThinkNote

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ThinkNote

Source code for our paper : Enhancing Knowledge Integration and Utilization of Large Language Models via Constructivist Cognition Modeling

We are currently optimizing the code and have uploaded the original version.

Quick Start

1️⃣ Install from git

git clone https://github.com/OpenMatch/ThinkNote
cd ThinkNote

2️⃣ Install the necessary packages

pip install -r requirements.txt

3️⃣ Set your own api here.

MODEL = "EMPTY"
openai_api_key = "EMPTY"
openai_api_base = "EMPTY"

4️⃣ Run the following script:

python -m scripts.run --dataset nq --topk 5

5️⃣ Analyzing logs:

python -m scripts.build --dataset nq --topk 5

6️⃣ Evaluate:

python -m scripts.evaluate --dataset nq --topk 5

Citation

@article{xu2024thinknote,
  title={ThinkNote: Enhancing Knowledge Integration and Utilization of Large Language Models via Constructivist Cognition Modeling},
  author={Xu, Zhipeng and Liu, Zhenghao and Yan, Yukun and Wang, Shuo and Yu, Shi and Zeng, Zheni and Xiao, Chaojun and Liu, Zhiyuan and Yu, Ge and Xiong, Chenyan},
  journal={arXiv preprint arXiv:2402.13547},
  year={2024}
}

About

This is the code repo for our paper "Enhancing Knowledge Integration and Utilization of Large Language Models via Constructivist Cognition Modeling".

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages