shmsw25 / FActScore

A package to evaluate factuality of long-form generation. Original implementation of our EMNLP 2023 paper "FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation"
https://arxiv.org/abs/2305.14251
MIT License
292 stars 43 forks source link

Maintaining core factscore in a new repository #47

Open armingh2000 opened 7 months ago

armingh2000 commented 7 months ago

I have created a Python package for extracting facts from texts and scoring them based on knowledge sources. This package is maintained and up-to-date with the latest OpenAI APIs. You can access the package in the following links:

https://pypi.org/project/FactScoreLite/ https://github.com/armingh2000/FactScoreLite

If anyone wants to improve/fix/change any functionalities, feel free to contribute.