梳理大模型生成科学创意的方法与局限，帮研究者选对工具。
Large Language Models for Scientific Idea Generation: A Creativity-Centered Survey
- 按知识增强、提示引导等五类方法分类大模型创意生成
- 用创造力框架分析不同方法的创新程度与科学合理性平衡
- 适合科研人员探索大模型辅助发现新思路
科学创意生成是发现的核心，需兼顾新颖性与科学合理性。不同于常规推理或通用创作，科学构思具有高度开放性和多目标特性，自动化尤为困难。近期大语言模型（LLM）已能生成连贯且可信的科学设想，但其创造力本质与边界仍不明确。本综述系统归纳了基于LLM的科学创意生成方法，聚焦不同策略在新颖性与科学有效性之间的权衡。我们将现有方法分为五类：外部知识增强、基于提示的分布引导、推理时扩展、多智能体协作和参数级调整。通过采用两种互补的创造力框架——Boden分类体系用于刻画预期创新层次，Rhodes四要素框架用于分析各方法强调的创造力来源，实现方法演进与认知创造力理论的对齐。该综述厘清了评估体系，指出了可靠、系统化大模型科学发现的关键挑战与未来方向。
原文摘要 · Abstract (English)
Scientific idea generation is central to discovery, requiring the joint satisfaction of novelty and scientific soundness. Unlike standard reasoning or general creative generation, scientific ideation is inherently open-ended and multi-objective, making its automation particularly challenging. Recent advances in large language models (LLMs) have enabled the generation of coherent and plausible scientific ideas, yet the nature and limits of their creative capabilities remain poorly understood. This survey provides a structured synthesis of methods for LLM-driven scientific ideation, focusing on how different approaches trade off novelty and scientific validity. We organize existing methods into five complementary families: External knowledge augmentation, Prompt-based distributional steering, Inference-time scaling, Multi-agent collaboration, and Parameter-level adaptation. To interpret their contributions, we adopt two complementary creativity frameworks: Boden taxonomy to characterize the expected level of creative novelty, and Rhodes 4Ps framework to analyze the aspects or sources of creativity emphasized by each method. By aligning methodological developments with cognitive creativity frameworks, this survey clarifies the evaluation landscape and identifies key challenges and directions for reliable and systematic LLM-based scientific discovery.
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。