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

科學思想生成是科學發現的核心，它驅動著人類進步——無論是通過解決未解難題，還是提出新穎假說來解釋未知現象。與標準的科學推理或一般創造性生成不同，科學領域的思想生成是一項多目標、開放式的任務，其中貢獻的新穎性與其實證嚴謹性同等重要。大型語言模型（LLMs）近年來已成為極具潛力的科學思想生成工具，能夠憑藉驚人的直覺和可接受的推理產出連貫且符合事實的內容，但其創造能力仍存在不穩定性且缺乏深入理解。本文對LLM驅動的科學思想生成方法進行了結構化綜述，探討不同方法如何平衡創造力與科學嚴謹性。我們將現有方法歸納為五類互補的範疇：外部知識增強、基於提示的分佈導向、推理時尺度調整、多智能體協作以及參數層級適應。為闡釋其貢獻，我們採用兩個互補框架：以博登的創造力分類法（組合型、探索型與變革型）來界定各類方法預期生成的思想層級，並藉助羅茲的4P框架（人格、過程、環境與產物）來定位各方法強調的創造力維度。通過將方法論進展與創造力框架相結合，本文明晰了該領域的發展現狀，並為實現LLM在科學發現中可靠、系統化且具變革性的應用指明關鍵方向。

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