Hallucination Detection on LLM-generated screenplays Story 2
100PrecisionAtlas
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| Atlas2026.07 | 100 | 84.6 | 91.7 | — | — | — | — | |
| AtlasEvaluator=GPT-5.42026.07 | 100 | 84.6 | 91.7 | 13 | 11 | 0 | 2 | |
| LLM-as-a-Judge2026.07 | 84.6 | 84.6 | 84.6 | — | — | — | — | |
| LLM-as-a-JudgeEvaluator=GPT-5.42026.07 | 84.6 | 84.6 | 84.6 | 13 | 11 | 2 | 2 |