OpenMOSS/HalluQA

Dataset and evaluation script for "Evaluating Hallucinations in Chinese Large Language Models"

34
/ 100
Emerging

This project helps evaluate how often Chinese Large Language Models (LLMs) generate incorrect or made-up information, a problem known as hallucination. It provides a benchmark dataset of carefully designed Chinese questions, along with scripts to assess your model's answers. The output is a "non-hallucination rate" or accuracy score, indicating your model's reliability. This is for researchers, product managers, or anyone working with Chinese LLMs who needs to quantify and improve their models' factual accuracy.

136 stars. No commits in the last 6 months.

Use this if you need to measure and compare the hallucination rates of various Chinese Large Language Models, especially for tasks involving knowledge or sensitive information.

Not ideal if you are working with non-Chinese LLMs or if your primary concern is not model hallucination.

Large Language Models NLP Evaluation AI Trustworthiness Chinese AI Hallucination Detection
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

136

Forks

6

Language

Python

License

Apache-2.0

Last pushed

Jun 05, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/OpenMOSS/HalluQA"

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