HaDes
Introduced by Liu et al. in A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation
HaDes is a token-level, reference-free hallucination detection dataset named HAllucination DEtection dataSet. To create this dataset, a large number of text segments extracted from English language Wikipedia are perturbed, and then verified these with crowd-sourced annotations.
Papers
| Paper | Code | Results | Date | Stars |
|---|
Dataset Loaders
No data loaders found. You can
submit your data loader here.
No data loaders found. You can
submit your data loader here.
