Hallucination Detection on LLM-generated screenplays Story 3
75PrecisionAtlas
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| Atlas2026.07 | 75 | 81.8 | 78.3 | — | — | — | — | |
| AtlasEvaluator=GPT-5.42026.07 | 75 | 81.8 | 78.3 | 11 | 9 | 3 | 2 | |
| LLM-as-a-Judge2026.07 | 69.2 | 81.8 | 75 | — | — | — | — | |
| LLM-as-a-JudgeEvaluator=GPT-5.42026.07 | 69.2 | 81.8 | 75 | 11 | 9 | 4 | 2 |