用动态上下文让大模型生成连贯分支故事，效果远超无上下文记忆的旧方法。
Multiverse of Greatness: Generating Story Branches with LLMs
- 设计动态上下文提示框架，让大模型记住故事历史并生成连贯剧情。
- 有上下文记忆的生成结果在客观评估中显著优于仅依赖初始数据的基线。
- 发现不同大模型家族均存在词语偏好和情感偏向，适合关注叙事生成的研究者。
本文提出动态上下文提示/编程（DCP/P）框架，通过动态上下文窗口历史与大语言模型交互，生成基于图结构的内容。尽管已有研究使用大模型生成视觉小说游戏，但此前方法依赖手动输出提取，且难以生成更长、更连贯的故事。我们对比了不提供上下文历史的基线方法与引入上下文记忆的DCP/P。客观评估显示，仅提供摘要的模型表现不佳，而结合完整故事上下文的模型生成质量显著提升。我们还进行了详尽的定性分析，比较两种方法下表现最优生成游戏的质量，并考察生成内容中的词汇选择与情感倾向。结果发现，即使使用不同大模型家族，也普遍存在对特定词汇的偏好。最后，论文讨论了未来研究的潜在方向。
原文摘要 · Abstract (English)
This paper presents Dynamic Context Prompting/Programming (DCP/P), a novel framework for interacting with LLMs to generate graph-based content with a dynamic context window history. While there is an existing study utilizing LLMs to generate a visual novel game, the previous study involved a manual process of output extraction and did not provide flexibility in generating a longer, coherent story. We evaluate DCP/P against our baseline, which does not provide context history to an LLM and only relies on the initial story data. Through objective evaluation, we show that simply providing the LLM with a summary leads to a subpar story compared to additionally providing the LLM with the proper context of the story. We also provide an extensive qualitative analysis and discussion. We qualitatively examine the quality of the objectively best-performing generated game from each approach. In addition, we examine biases in word choices and word sentiment of the generated content. We find a consistent observation with previous studies that LLMs are biased towards certain words, even with a different LLM family. Finally, we provide a comprehensive discussion on opportunities for future studies.
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。