PlotTwist: A Creative Plot Generation Framework with Small Language Models
Abhinav Thorat, Ravi Kolla, Jyotin Goel, Niranjan Pedanekar

TL;DR
PlotTwist is a framework that enables small language models with up to 5 billion parameters to generate high-quality, premise-conditioned creative plots, rivaling much larger models through structured, preference-based alignment techniques.
Contribution
It introduces a novel structured framework combining specialized components and preference optimization to enhance creative plot generation with small language models.
Findings
Outperforms larger models in narrative quality dimensions
Effectively distinguishes between critically acclaimed and poor plots
Demonstrates resource-efficient high-quality plot generation
Abstract
Creative plot generation presents a fundamental challenge for language models: transforming a concise premise into a coherent narrative that sustains global structure, character development, and emotional resonance. Although recent Large Language Models (LLMs) demonstrate strong fluency across general-purpose tasks, they typically require preference alignment to perform well on specialized domains such as creative plot generation. However, conducting such alignment at the scale of frontier LLMs is computationally prohibitive, significantly limiting accessibility and practical deployment. To address this, we present PlotTwist, a structured framework that enables Small Language Models (SLMs) with 5B active parameters to generate high-quality, premise-conditioned plots competitive with frontier systems up to larger. Our approach decomposes generation into three…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsArtificial Intelligence in Games · Topic Modeling · Multimodal Machine Learning Applications
