intuit/sac3

Official repo for SAC3: Reliable Hallucination Detection in Black-Box Language Models via Semantic-aware Cross-check Consistency

38
/ 100
Emerging

This tool helps ensure the accuracy of responses from large language models (LLMs) by detecting when they generate incorrect or made-up information, known as 'hallucinations.' It takes a question and a target answer as input, then checks the LLM's consistency across multiple variations of the question and against additional verification models. The output indicates how reliably the LLM provides factual answers, making it useful for anyone deploying LLMs in production applications where accuracy is critical.

No commits in the last 6 months.

Use this if you need to confidently assess whether a large language model's outputs are factually correct and consistent, especially when the LLM is a 'black-box' system you can't directly inspect.

Not ideal if you are looking for a tool to improve the stylistic quality or fluency of LLM outputs, as its focus is solely on factual accuracy and consistency.

AI quality assurance LLM evaluation factual verification generative AI model validation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

39

Forks

7

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Jan 18, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/intuit/sac3"

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