Research map / Large language models / Language, safety and interpretability
Automated Storytelling via Causal, Commonsense Plot Ordering
Prithviraj Ammanabrolu, Wesley Cheung, William Broniec, Mark O. Riedl
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| C2PO vs BERT+infill (soft causal needs/wants ordering) | C2PO · mystery and fairy tale, all six questions | human preference | Improved |
| C2PO vs BERT+infill on enjoyability and genre fit | C2PO · mystery genre | human preference | Improved |
| C2PO vs BERT+infill on single plot | C2PO · mystery genre | human preference | Improved |
| C2PO vs BERT+infill on plausible ordering, causal sense, single plot | C2PO · fairy tale genre | human preference | Improved |
| C2PO vs BERT+infill on genre fit and enjoyability | C2PO · fairy tale genre | human preference | Improved |
| C2PO vs Hierarchical Fusion on ordering, causal sense, single plot, quality | C2PO · mystery genre | human preference | Improved |
| C2PO vs Hierarchical Fusion on enjoyment and genre resemblance | C2PO · mystery genre | human preference | No clear effect |
| C2PO vs Hierarchical Fusion on ordering, causal sense, single plot, quality | C2PO · fairy tale genre | human preference | Improved |
| C2PO vs Hierarchical Fusion on enjoyment and genre resemblance | C2PO · fairy tale genre | human preference | No clear effect |
| commonsense reasoning without storytelling bias (BERT+infill style) | commonsense language models · enjoyability and genre resemblance | human preference | Hurt |
| genre-specific commonsense mismatch (fairy tales vs mysteries) | C2PO vs BERT+infill · enjoyability and genre resemblance | human preference: 0.56 | Mixed |
| Hierarchical Fusion storytelling bias vs C2PO | Hierarchical Fusion · generated stories mystery | unique trigrams: 1245 -> 2187 | Mixed |
Closest papers by meaning
- Plan-and-Write: Towards Better Automatic Storytelling (AAAI 2019 · similarity 0.87)
- LogiStory: A Logic-Aware Framework for Multi-Image Story Visualization (ICLR 2026 · similarity 0.84)
- Agents' Room: Narrative Generation through Multi-step Collaboration (ICLR 2025 · similarity 0.83)
- NarrativeBridge: Enhancing Video Captioning with Causal-Temporal Narrative (ICLR 2025 · similarity 0.83)
- NaRuto: Automatically Acquiring Planning Models from Narrative Texts (AAAI 2024 · similarity 0.83)
- VinaBench: Benchmark for Faithful and Consistent Visual Narratives (CVPR 2025 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
