用双向搜索生成结构完整、主题深刻的中文长篇小说
BiT-MCTS: A Theme-based Bidirectional MCTS Approach to Chinese Fiction Generation
- 以高潮为起点，双向扩展剧情，遵循戏剧结构理论
- 相比基线方法，故事更长且逻辑更连贯，人类评价更高
- 适合想提升叙事能力的创作者和研究者
从开放主题生成长篇线性小说仍是大语言模型的重大挑战，传统基于前提或线性提纲的方法常难以保证全局结构与情节多样性。本文提出 BiT-MCTS，一种基于主题的框架，受弗莱塔格金字塔启发，采用“高潮先行、双向扩展”策略。给定主题后，方法提取核心戏剧冲突并生成明确高潮，再通过双向蒙特卡洛树搜索（MCTS）分别向后（回落、结局）和向前（上升、铺垫）扩展剧情，形成结构化大纲。最后一步根据优化后的提纲生成完整叙事。我们构建了中文主题语料库用于评估，并在三种主流大语言模型上进行了广泛实验。结果表明，相较于强基线，BiT-MCTS 在叙事连贯性、情节结构和主题深度方面均有提升，且在自动指标与人工评估中均能生成更长、更连贯的故事。
原文摘要 · Abstract (English)
Generating long-form linear fiction from open-ended themes remains a major challenge for large language models, which frequently fail to guarantee global structure and narrative diversity when using premise-based or linear outlining approaches. We present BiT-MCTS, a theme-driven framework that operationalizes a "climax-first, bidirectional expansion" strategy motivated by Freytag's Pyramid. Given a theme, our method extracts a core dramatic conflict and generates an explicit climax, then employs a bidirectional Monte Carlo Tree Search (MCTS) to expand the plot backward (rising action, exposition) and forward (falling action, resolution) to produce a structured outline. A final generation stage realizes a complete narrative from the refined outline. We construct a Chinese theme corpus for evaluation and conduct extensive experiments across three contemporary LLM backbones. Results show that BiT-MCTS improves narrative coherence, plot structure, and thematic depth relative to strong baselines, while enabling substantially longer, more coherent stories according to automatic metrics and human judgments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。