DOC: Improving Long Story Coherence With Detailed Outline Control
Not on the map. Why?
Abstract (arXiv)
We propose the Detailed Outline Control (DOC) framework for improving long-range plot coherence when automatically generating several-thousand-word-long stories. DOC consists of two complementary components: a detailed outliner and a detailed controller. The detailed outliner creates a more detailed, hierarchically structured outline, shifting creative burden from the main drafting procedure to the planning stage. The detailed controller ensures the more detailed outline is still respected during generation by controlling story passages to align with outline details. In human evaluations of automatically generated stories, DOC substantially outperforms a strong Re3 baseline (Yang et al., 2022) on plot coherence (22.5% absolute gain), outline relevance (28.2%), and interestingness (20.7%). Humans also judged DOC to be much more controllable in an interactive generation setting.
Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Dec 2022.
Builds on
0 of 0 references.
No references here yet.
Built on by
Citing papers per year: 2023: 4; 2024: 1; 2025: 4; 2026: 2.
11 papers.
- 2023Challenges and Applications of Large Language Modelscited by 251
- 2023Rehearsal: Simulating Conflict to Teach Conflict Resolutioncited by 54
- 2023Interactive Natural Language Processingcited by 31
- 2023Improving Pacing in Long-Form Story Planningcited by 21
- 2025OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinkingcited by 18
- 2024THOUGHTSCULPT: Reasoning with Intermediate Revision and Searchcited by 11
- 2025EvolvR: Self-Evolving Pairwise Reasoning for Story Evaluation to Enhance Generationcited by 2
- 2025CLEAR: Contrasting Textual Feedback with Experts and Amateurs for Reasoningcited by 0
- 2025COIG-Writer: A High-Quality Dataset for Chinese Creative Writing with Thought Processescited by 0
- 2026Implementing surrogate goals for safer bargaining in LLM-based agentscited by 0
- 2026Shadow-Loom: Causal Reasoning over Graphical World Models of Narrativescited by 0
- 2026Shadow-Loom: Causal Reasoning over Graphical World Models of Narratives4 May 2026
- 2026Implementing surrogate goals for safer bargaining in LLM-based agents6 Apr 2026
- 2025COIG-Writer: A High-Quality Dataset for Chinese Creative Writing with Thought Processes16 Oct 2025
- 2025EvolvR: Self-Evolving Pairwise Reasoning for Story Evaluation to Enhance Generation8 Aug 2025
- 2025CLEAR: Contrasting Textual Feedback with Experts and Amateurs for Reasoning24 Mar 2025
- 2025OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking16 Jan 2025
- 2024THOUGHTSCULPT: Reasoning with Intermediate Revision and Search9 Apr 2024
- 2023Improving Pacing in Long-Form Story Planning8 Nov 2023
- 2023Rehearsal: Simulating Conflict to Teach Conflict Resolution21 Sep 2023
- 2023Challenges and Applications of Large Language Models19 Jul 2023
- 2023Interactive Natural Language Processing22 May 2023