Redaction: MaskLM vs Claude Haiku vs GLiNER
Pick a kind of document for a random example, or paste your own, and see what each model hides. Examples come with a human-annotated answer key and were never seen in training. On the results page, change how redactions look, hold Reveal to peek underneath, and slide the confidence to hide more or less.
Random example
Types
Samples use their dataset's instruction; your own text uses the de-identification instruction. Both are editable.
Redaction result
MaskLM
Baseline
Answer key (human annotation)
Where they differ
Claude Haiku answers with strings, which are located in the text. Scores follow the slider: “whole items right” matches each found item to one answer-key item; “text marked right” counts the characters marked.