PlotTwist: A Creative Plot Generation Framework with Small Language Models

• URL: http://arxiv.org/abs/2603.16410v1
• Date: Tue, 17 Mar 2026 11:45:04 GMT
• Title: PlotTwist: A Creative Plot Generation Framework with Small Language Models
• Abstract summary: PlotTwist is a structured framework that enables Small Language Models (SLMs) with $leq$ 5B active parameters to generate high-quality, premise-conditioned plots.<n>Our approach decomposes generation into three specialized components: (1) an Aspect Rating Reward Model trained via a novel Positive-Negative prompting strategy to deliver structured narratives across five Narrative Quality Dimensions (NQDs); (2) a Mixture-of-Experts plot generator aligned via Direct Optimization Preference on high-confidence preference pairs; and (3) an Agentic Evaluation module that emulates human critical judgment for unbiased post-hoc assessment.
• Score: 2.2904707352645386
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• 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 $\leq$ 5B active parameters to generate high-quality, premise-conditioned plots competitive with frontier systems up to $200\times$ larger. Our approach decomposes generation into three specialized components: (1) an Aspect Rating Reward Model trained via a novel Positive-Negative prompting strategy to deliver structured narratives across five Narrative Quality Dimensions (NQDs); (2) a Mixture-of-Experts (MoE) plot generator aligned via Direct Preference Optimization on high-confidence preference pairs; and (3) an Agentic Evaluation module that emulates human critical judgment for unbiased post-hoc assessment. Extensive experiments demonstrate that PlotTwist consistently outperforms frontier models across multiple NQDs despite substantially tighter capacity constraints. Further validation confirms strong sensitivity to narrative quality, as the framework reliably distinguishes plots derived from critically acclaimed versus widely panned screenplays. Together, these results establish structured, preference-based alignment as a resource-efficient approach to high-quality creative plot generation.

Related papers

• SignDPO: Multi-level Direct Preference Optimisation for Skeleton-based Gloss-free Sign Language Translation [52.752934028506274]
  We present SignDPO, a novel multi-level Direct Preference optimisation framework.<n>We show that SignDPO consistently outperforms state-of-the-art gloss-free methods.<n>Our results suggest that multi-level preference alignment is a powerful paradigm for bridging the gap between high-entropy skeletal trajectories and discrete linguistic semantics.
  arXiv  Detail & Related papers  (2026-04-20T09:59:18Z)
• UniCreative: Unifying Long-form Logic and Short-form Sparkle via Reference-Free Reinforcement Learning [14.788245475904924]
  We propose textbfUniCreative, a unified reference-free reinforcement learning framework.<n>We first introduce textbfAC-GenRM, an adaptive constraint-aware reward model that dynamically synthesizes query-specific criteria to provide fine-grained preference judgments.<n>We then propose textbfACPO, a policy optimization algorithm that aligns models with human preferences across both content quality and structural paradigms without supervised fine-tuning and ground-truth references.
  arXiv  Detail & Related papers  (2026-04-07T07:15:28Z)
• CDRRM: Contrast-Driven Rubric Generation for Reliable and Interpretable Reward Modeling [61.75914342638658]
  CDRRM (Contrast-Driven Reward Model) is a framework for high-quality rubric generation and guided preference judgment.<n>This work offers a scalable, interpretable, and data-efficient path for reward modeling.
  arXiv  Detail & Related papers  (2026-03-09T07:15:23Z)
• SSR: Pushing the Limit of Spatial Intelligence with Structured Scene Reasoning [30.87517633729756]
  SSR is a framework designed for Structured Scene Reasoning.<n>It seamlessly integrates 2D and 3D representations via a lightweight alignment mechanism.<n>It achieves state-of-the-art performance on multiple spatial intelligence benchmarks.
  arXiv  Detail & Related papers  (2026-02-28T02:05:35Z)
• DraCo: Draft as CoT for Text-to-Image Preview and Rare Concept Generation [69.69738832428543]
  We propose Draft-as-CoT (DraCo), a novel interleaved reasoning paradigm for enhanced text-to-image generation.<n>Our method first generates a low-resolution draft image as preview, providing more concrete and structural visual planning and guidance.<n>DraCo achieves a tremendous increase on GenEval (+8%), Imagine-Bench (+0.91), and GenEval++ (+3%)
  arXiv  Detail & Related papers  (2025-12-04T18:59:53Z)
• AI-Salesman: Towards Reliable Large Language Model Driven Telemarketing [79.0112532518727]
  We release TeleSalesCorpus, the first real-world-grounded dialogue dataset for this domain.<n>We then propose AI-Salesman, a novel framework featuring a dual-stage architecture.<n>We show that our proposed AI-Salesman significantly outperforms baseline models in both automatic metrics and comprehensive human evaluations.
  arXiv  Detail & Related papers  (2025-11-15T09:44:42Z)
• Understanding and Improving Length Generalization in Hierarchical Sparse Attention Models [33.99822400076112]
  Chunk-based sparse attention has emerged as a promising paradigm for extreme length generalization.<n>We present a systematic dissection of these models to identify the core components driving their performance.<n>We establish a new state-of-the-art for training-free length extrapolation, successfully generalizing models trained on a 4K context to 32 million tokens on RULER and BABILong.
  arXiv  Detail & Related papers  (2025-10-20T06:17:57Z)
• COIG-Writer: A High-Quality Dataset for Chinese Creative Writing with Thought Processes [83.84578306665976]
  Large language models exhibit systematic deficiencies in creative writing, particularly in non-English contexts.<n>We present COIG-Writer, a novel Chinese creative writing dataset that captures both diverse outputs and their underlying thought processes.
  arXiv  Detail & Related papers  (2025-10-16T15:01:19Z)
• Large Language Model-Based Automatic Formulation for Stochastic Optimization Models [0.0]
  This paper presents the first integrated systematic study on the performance of large language models (LLMs)<n>We design several prompts that guide ChatGPT through structured tasks using chain-of- thought and modular reasoning.<n>Across a diverse set of problems, GPT-4-Turbo outperforms other models in partial score, variable matching, objective accuracy, with cot_s_instructions emerging as the most effective prompting strategies.
  arXiv  Detail & Related papers  (2025-08-24T03:31:25Z)
• Multi-Agent Synergy-Driven Iterative Visual Narrative Synthesis [2.846897538377738]
  We introduce RCPS, a novel framework for automated generation of high-quality media presentations.<n>We also propose PREVAL, a preference-based evaluation framework to assess presentation quality across Content, Coherence, and Design.<n>PREVAL shows strong correlation with human judgments, validating it as a reliable automated tool for assessing presentation quality.
  arXiv  Detail & Related papers  (2025-07-17T16:50:07Z)
• Precision-Recall Divergence Optimization for Generative Modeling with GANs and Normalizing Flows [54.050498411883495]
  We develop a novel training method for generative models, such as Generative Adversarial Networks and Normalizing Flows. We show that achieving a specified precision-recall trade-off corresponds to minimizing a unique $f$-divergence from a family we call the textitPR-divergences. Our approach improves the performance of existing state-of-the-art models like BigGAN in terms of either precision or recall when tested on datasets such as ImageNet.
  arXiv  Detail & Related papers  (2023-05-30T10:07:17Z)
• Model Criticism for Long-Form Text Generation [113.13900836015122]
  We apply a statistical tool, model criticism in latent space, to evaluate the high-level structure of generated text. We perform experiments on three representative aspects of high-level discourse -- coherence, coreference, and topicality. We find that transformer-based language models are able to capture topical structures but have a harder time maintaining structural coherence or modeling coreference.
  arXiv  Detail & Related papers  (2022-10-16T04:35:58Z)
• Retrieve-and-Fill for Scenario-based Task-Oriented Semantic Parsing [110.4684789199555]
  We introduce scenario-based semantic parsing: a variant of the original task which first requires disambiguating an utterance's "scenario" This formulation enables us to isolate coarse-grained and fine-grained aspects of the task, each of which we solve with off-the-shelf neural modules. Our model is modular, differentiable, interpretable, and allows us to garner extra supervision from scenarios.
  arXiv  Detail & Related papers  (2022-02-02T08:00:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.