面向科学创意生成的大语言模型：以创造力为核心的综述

摘要

科学思想生成是科学发现的核心驱动力，它通过解决未解难题或提出新假说解释未知现象，不断推动人类进步。与标准科学推理或普通创造性生成不同，科学思想生成具有多目标性和开放性，其创新性与实证严谨性同等重要。尽管大语言模型近期展现出作为科学思想生成器的潜力——能够产出具有惊人直觉和可接受推理的连贯事实性内容，但其创造能力仍存在不稳定性且认知有限。本文对LLM驱动的科学思想生成方法进行结构化梳理，审视不同方法如何平衡创造力与科学严谨性。我们将现有方法归纳为五个互补类别：外部知识增强、基于提示的分布导向、推理时缩放、多智能体协作以及参数级适应。为解析其贡献，我们采用两个互补框架：运用博登对组合型、探索型与变革型创造力的分类法来界定各类方法预期生成的思想层级，借助罗兹的4P框架（创造者、创造过程、创造环境、创造产物）定位各方法强调的创造力维度。通过将方法论进展与创造力理论框架对齐，本文厘清了该领域现状，并勾勒出实现LLM在科学发现中可靠化、系统化与变革性应用的关键路径。

English

Scientific idea generation lies at the heart of scientific discovery and has driven human progress-whether by solving unsolved problems or proposing novel hypotheses to explain unknown phenomena. Unlike standard scientific reasoning or general creative generation, idea generation in science is a multi-objective and open-ended task, where the novelty of a contribution is as essential as its empirical soundness. Large language models (LLMs) have recently emerged as promising generators of scientific ideas, capable of producing coherent and factual outputs with surprising intuition and acceptable reasoning, yet their creative capacity remains inconsistent and poorly understood. This survey provides a structured synthesis of methods for LLM-driven scientific ideation, examining how different approaches balance creativity with scientific soundness. We categorize 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 employ two complementary frameworks: Boden's taxonomy of Combinatorial, Exploratory and Transformational creativity to characterize the level of ideas each family expected to generate, and Rhodes' 4Ps framework-Person, Process, Press, and Product-to locate the aspect or source of creativity that each method emphasizes. By aligning methodological advances with creativity frameworks, this survey clarifies the state of the field and outlines key directions toward reliable, systematic, and transformative applications of LLMs in scientific discovery.

面向科学创意生成的大语言模型：以创造力为核心的综述

Large Language Models for Scientific Idea Generation: A Creativity-Centered Survey

摘要

Support