paper
referenced-only
1971
paper:doi-10-1037-h0031619Measuring nominal scale agreement among many raters.
ByJ. Fleiss
Similar preprints — Semantic Scholar
Cited by (1)
- Spotting Out-of-Character Behavior: Atomic-Level Evaluation of Persona Fidelity in Open-Ended Generation
Conventional response-level persona evaluation systematically inflates fidelity scores by collapsing multi-sentence outputs into a single score, masking sentence-level Out-of-Character (OOC) deviation