HaluEval

Evals

Benchmark / dataset

Large hallucination recognition benchmark.

Category
Hallucination & factuality
Insurance exposure
Hallucination
Publisher
Renmin University
Publisher type
Academic
License
MIT
Status
Stale (>12mo)
Last commit
2024-02-12
Stars
603

View source on GitHub →

Wanich Risk Lab, 2026.