PhantomFill Benchmark
Explore score history ↗PhantomFill measures schema-coerced fabrication in language models by asking questions on unanswerable inputs under three output formats: free text, JSON with an escape option, and JSON with required fields. It reports Coerced Fabrication Rate and Escape Utilization Rate.
- Released
- 2026-06-11
- Evaluates
- General AI, Language & Knowledge, cs.LG
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
PhantomFill paper and code
No reported scores are on record for this benchmark yet.