PKU-YuanGroup/Hallucination-Attack

Attack to induce LLMs within hallucinations

41
/ 100
Emerging

This project helps evaluate how easily large language models (LLMs) can be tricked into generating false information or 'hallucinations.' It takes a standard LLM and applies specially crafted, often nonsensical prompts to see if the model can be made to produce fake facts or news. This is useful for AI safety researchers, red teamers, and anyone responsible for assessing the reliability and potential risks of LLMs before deployment.

164 stars. No commits in the last 6 months.

Use this if you need to rigorously test an LLM's susceptibility to generating false or misleading content when given unusual or adversarial inputs.

Not ideal if you are looking to improve the factual accuracy of an LLM or fine-tune it for a specific task.

AI Safety LLM Evaluation Adversarial Testing AI Risk Assessment Model Red Teaming
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

164

Forks

21

Language

Python

License

MIT

Last pushed

May 17, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/PKU-YuanGroup/Hallucination-Attack"

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