用大模型生成科学创意，还自带评审系统验证想法质量。
Spark: A System for Scientifically Creative Idea Generation
- 结合检索增强与大模型生成科学创意。
- 用60万条科研评论训练评审模型Judge，自动评估创意价值。
- 开源数据集，推动可解释的科学创意生成研究。
近期大型语言模型（LLMs）在生成科学新研究想法方面展现出潜力，这一方向契合计算创造力（CC）的核心原则。为此，我们提出名为Spark的创意生成系统，通过检索增强的LLM生成创意，并引入一个基于OpenReview上60万条科研评审训练的评审模型Judge。本工作既是系统演示，也旨在激励其他CC研究者将科学创意的生成与评估建立在基础的计算创造力原则上。为此，我们公开了用于训练Judge的标注数据集，欢迎研究者探索大模型在创意生成与评估中的应用。
原文摘要 · Abstract (English)
Recently, large language models (LLMs) have shown promising abilities to generate novel research ideas in science, a direction which coincides with many foundational principles in computational creativity (CC). In light of these developments, we present an idea generation system named Spark that couples retrieval-augmented idea generation using LLMs with a reviewer model named Judge trained on 600K scientific reviews from OpenReview. Our work is both a system demonstration and intended to inspire other CC researchers to explore grounding the generation and evaluation of scientific ideas within foundational CC principles. To this end, we release the annotated dataset used to train Judge, inviting other researchers to explore the use of LLMs for idea generation and creative evaluations.
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。