Automatic Hallucination detection with SelfCheckGPT NLI
This Hugging Face article describes SelfCheckGPT NLI for detecting hallucinations in generated answers.
About Automatic Hallucination detection with SelfCheckGPT NLI
A Hugging Face community article by Daniel Huynh, published November 27, 2023. It explains SelfCheckGPT NLI, a method that draws several samples for the same prompt and checks them for inconsistencies, since higher inconsistency can point to hallucinated output from a large language model. The article reports an experiment on the score's precision and calibration, links a notebook to reproduce it, and offers a demo with example texts and an adjustable threshold.
Pricing is not clearly stated.
Key features
- Explains inconsistency-based scoring for LLM hallucinations
- Reports an experiment on precision and score calibration
- Links a notebook to reproduce the experiment
- Demo Space with example texts and threshold control
- Describes black-box use without weights or probabilities
- Covers summarization, free-form Q&A, and classification
Automatic Hallucination detection with SelfCheckGPT NLI at a glance
- Official website
- huggingface.co/blog/dhuynh95/automatic-halluci…
- Category
- AI & Machine Learning › AI Data & Analytics
- Type
- Publication
- Platforms
- Web
- Details verified
- Oct 21, 2026 · Official source
- Last checked
- Oct 5, 2026 · Online when checked
- Listed
- Oct 5, 2026
Popular in AI Data & Analytics
Well-known listings from the same topic.
Tell us and an editor will check it.
Claim the listing and suggest updates yourself. An editor checks every claim first.