Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

LLM-generated screenplays

Benchmarks

Task NameDataset NameSOTA ResultTrend
Hallucination DetectionLLM-generated screenplays Aggregate
Precision91.4
4
Hallucination DetectionLLM-generated screenplays Story 3
Precision75
4
Hallucination DetectionLLM-generated screenplays Story 2
Precision100
4
Hallucination DetectionLLM-generated screenplays Story 1
Precision100
4
Showing 4 of 4 rows