naver-ai/korean-safety-benchmarks
Official datasets and pytorch implementation repository of SQuARe and KoSBi (ACL 2023)
This project helps researchers and developers ensure that large language models (LLMs) used in Korean contexts respond appropriately to sensitive questions and avoid social biases. It provides two datasets: SQuARe, containing sensitive questions and acceptable responses, and KoSBi, for detecting and mitigating social biases. The intended users are AI researchers and developers working on LLMs, especially those focused on safety and fairness in Korean-language applications.
249 stars. No commits in the last 6 months.
Use this if you are developing or evaluating large language models for the Korean language and need to ensure they are safe, unbiased, and provide acceptable responses to sensitive topics.
Not ideal if your work is outside of Korean language models or if you are not a developer or researcher in the field of AI and natural language processing.
Stars
249
Forks
18
Language
Python
License
MIT
Category
Last pushed
Jun 29, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/naver-ai/korean-safety-benchmarks"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
luheng/deep_srl
Code and pre-trained model for: Deep Semantic Role Labeling: What Works and What's Next
sileod/tasksource
Datasets collection and preprocessings framework for NLP extreme multitask learning
loomchild/maligna
Bilingual sengence aligner
CK-Explorer/DuoSubs
Semantic subtitle aligner and merger for bilingual subtitle syncing.
coastalcph/lex-glue
LexGLUE: A Benchmark Dataset for Legal Language Understanding in English