Script Generation on Narrative Generation Dataset Script
94Narrative Structure ScorePLOTTER
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| PLOTTERBackbone=DeepSeek R1, Comparative Baseline=LLM Plan and Write2026.04 | 94 | 100 | 100 | 98 | 94 | |
| PLOTTERBackbone=GPT4.1, Comparative Baseline=DOC2026.04 | 92 | 86 | 92 | 92 | 44 | |
| PLOTTERBackbone=Qwen3, Comparative Baseline=LLM Plan and Write2026.04 | 88 | 100 | 100 | 96 | 68 | |
| PLOTTERBackbone=DeepSeek R1, Comparative Baseline=DOC2026.04 | 84 | 76 | 86 | 86 | 48 | |
| PLOTTERBackbone=Qwen3, Comparative Baseline=DOC2026.04 | 78 | 76 | 80 | 78 | 60 | |
| PLOTTERBackbone=GPT4.1, Comparative Baseline=Dramatron2026.04 | 74 | 90 | 76 | 72 | 14 | |
| PLOTTERBackbone=GPT4.1, Comparative Baseline=LLM Plan and Write2026.04 | 72 | 100 | 100 | 96 | 40 | |
| PLOTTERBackbone=Qwen3, Comparative Baseline=Dramatron2026.04 | 64 | 84 | 70 | 60 | 16 | |
| DramatronBackbone=DeepSeek R1, Comparative Baseline=PLOTTER2026.04 | 52 | 50 | 42 | 46 | 4 | |
| PLOTTERBackbone=DeepSeek R1, Comparative Baseline=Dramatron2026.04 | 48 | 50 | 58 | 54 | 8 | |
| DramatronBackbone=Qwen3, Comparative Baseline=PLOTTER2026.04 | 36 | 16 | 30 | 40 | 2 | |
| LLM Plan and WriteBackbone=GPT4.1, Comparative Baseline=PLOTTER2026.04 | 28 | 0 | 0 | 4 | 18 | |
| DOCBackbone=Qwen3, Comparative Baseline=PLOTTER2026.04 | 22 | 24 | 20 | 22 | 26 | |
| DramatronBackbone=GPT4.1, Comparative Baseline=PLOTTER2026.04 | 16 | 10 | 20 | 28 | 0 | |
| DOCBackbone=DeepSeek R1, Comparative Baseline=PLOTTER2026.04 | 16 | 24 | 14 | 14 | 32 | |
| LLM Plan and WriteBackbone=Qwen3, Comparative Baseline=PLOTTER2026.04 | 12 | 0 | 0 | 4 | 14 | |
| DOCBackbone=GPT4.1, Comparative Baseline=PLOTTER2026.04 | 8 | 14 | 8 | 8 | 16 | |
| LLM Plan and WriteBackbone=DeepSeek R1, Comparative Baseline=PLOTTER2026.04 | 6 | 0 | 0 | 2 | 2 |