arian-askari/ChatGPT-RetrievalQA-CIKM2023

A dataset for training/evaluating Question Answering Retrieval models on ChatGPT responses with the possibility to training/evaluating on real human responses.

26
/ 100
Experimental

This project provides a unique dataset for anyone working on improving how search engines and question-answering systems retrieve information. It offers collections of questions paired with answers generated by ChatGPT and by human experts. The goal is to help evaluate if AI-generated text can be used effectively to train and test information retrieval models, providing a valuable resource for information retrieval researchers and developers.

142 stars. No commits in the last 6 months.

Use this if you are a researcher or developer focused on building or improving search and question-answering systems and want to evaluate using large language model outputs as training data.

Not ideal if you are looking for a ready-to-use search engine or a solution for generating human-like text directly.

information-retrieval question-answering-systems search-engine-development natural-language-processing AI-model-evaluation
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 8 / 25

How are scores calculated?

Stars

142

Forks

7

Language

Jupyter Notebook

License

Last pushed

Jan 15, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/arian-askari/ChatGPT-RetrievalQA-CIKM2023"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.