HAT: Hallucination Annotation for Translation

HAT: Hallucination Annotation for Translation 🧭 Table of Contents Overview Usage Data Creation Process Data Statistics Dataset Structure Paper Abstract Citation License 📘 Overview HAT (Hallucination Annotation for Translation) is a large-scale dataset for hallucination detection in machine translation (MT).It is released as part of our publication at ACL 2026 (paper). 350,959 span-level annotated samples 38 language pairs ~8,000-10,000… See the full description on the dataset page:

Source: Hugging Face Hub (apple/hat). Metadata imported from the dataset’s Hub tags.