Storyline Generation on Narrative Generation Storyline
100Narrative ScorePLOTTER
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| PLOTTERBackbone=GPT4.1, Comparative Baseline=Dramatron2026.04 | 100 | 100 | 100 | 98 | 2 | |
| PLOTTERBackbone=GPT4.1, Comparative Baseline=LLM Plan and Write2026.04 | 94 | 100 | 100 | 100 | 34 | |
| PLOTTERBackbone=DeepSeek R1, Comparative Baseline=LLM Plan and Write2026.04 | 94 | 100 | 98 | 98 | 94 | |
| PLOTTERBackbone=Qwen3, Comparative Baseline=LLM Plan and Write2026.04 | 86 | 100 | 100 | 92 | 66 | |
| PLOTTERBackbone=Qwen3, Comparative Baseline=DOC2026.04 | 70 | 74 | 80 | 72 | 22 | |
| PLOTTERBackbone=Qwen3, Comparative Baseline=Dramatron2026.04 | 64 | 92 | 92 | 70 | 8 | |
| PLOTTERBackbone=GPT4.1, Comparative Baseline=DOC2026.04 | 62 | 86 | 90 | 66 | 10 | |
| PLOTTERBackbone=DeepSeek R1, Comparative Baseline=DOC2026.04 | 52 | 60 | 72 | 54 | 18 | |
| DOCBackbone=DeepSeek R1, Comparative Baseline=PLOTTER2026.04 | 48 | 40 | 28 | 46 | 30 | |
| DramatronBackbone=DeepSeek R1, Comparative Baseline=PLOTTER2026.04 | 44 | 18 | 38 | 48 | 4 | |
| PLOTTERBackbone=DeepSeek R1, Comparative Baseline=Dramatron2026.04 | 42 | 82 | 60 | 52 | 4 | |
| DOCBackbone=GPT4.1, Comparative Baseline=PLOTTER2026.04 | 38 | 14 | 10 | 34 | 16 | |
| DramatronBackbone=Qwen3, Comparative Baseline=PLOTTER2026.04 | 32 | 8 | 8 | 28 | 8 | |
| DOCBackbone=Qwen3, Comparative Baseline=PLOTTER2026.04 | 30 | 26 | 20 | 28 | 34 | |
| LLM Plan and WriteBackbone=Qwen3, Comparative Baseline=PLOTTER2026.04 | 14 | 0 | 0 | 8 | 12 | |
| LLM Plan and WriteBackbone=GPT4.1, Comparative Baseline=PLOTTER2026.04 | 6 | 0 | 0 | 0 | 18 | |
| LLM Plan and WriteBackbone=DeepSeek R1, Comparative Baseline=PLOTTER2026.04 | 6 | 0 | 2 | 2 | 2 | |
| DramatronBackbone=GPT4.1, Comparative Baseline=PLOTTER2026.04 | 0 | 0 | 0 | 2 | 0 |