用拆解关键词发现新科学概念，让AI自己搞出有创意又靠谱的科研想法。
Spacer: Towards Engineered Scientific Inspiration
- 把论文拆成关键词，从陌生连接中激发新思路。
- 能从关键词重建顶刊论文核心观点，85%以上合理。
- 适合想快速生成创新科研点的研究者使用。
大语言模型的进展使自动化科学研究成为通往人工超智能的关键一步。然而，现有系统要么局限于狭窄任务，要么受限于LLM的创造力。我们提出Spacer，一个无需外部干预即可生成兼具创造性和事实依据科学概念的发现系统。其核心是‘刻意去语境化’：将信息分解为原子级关键词，并挖掘它们之间未探索的关联。Spacer由两部分组成：(i) Nuri，一个从18万篇生物领域学术论文构建的关键词图中提取高潜力关键词集的灵感引擎；(ii) 构思管道（Manifesting Pipeline），将关键词集转化为完整的科学陈述。该管道通过分析关键词间逻辑关系、验证合理性并最终生成原创科学概念。实验表明，Nuri的评估指标在区分高影响力论文上获得0.737的AUROC。构思管道仅凭关键词集成功重构了最新顶刊文章的核心概念，基于LLM评分，超过85%的情况具有合理性。嵌入空间分析显示，Spacer输出与顶尖论文的相似度显著高于当前SOTA LLM。
原文摘要 · Abstract (English)
Recent advances in LLMs have made automated scientific research the next frontline in the path to artificial superintelligence. However, these systems are bound either to tasks of narrow scope or the limited creative capabilities of LLMs. We propose Spacer, a scientific discovery system that develops creative and factually grounded concepts without external intervention. Spacer attempts to achieve this via 'deliberate decontextualization,' an approach that disassembles information into atomic units - keywords - and draws creativity from unexplored connections between them. Spacer consists of (i) Nuri, an inspiration engine that builds keyword sets, and (ii) the Manifesting Pipeline that refines these sets into elaborate scientific statements. Nuri extracts novel, high-potential keyword sets from a keyword graph built with 180,000 academic publications in biological fields. The Manifesting Pipeline finds links between keywords, analyzes their logical structure, validates their plausibility, and ultimately drafts original scientific concepts. According to our experiments, the evaluation metric of Nuri accurately classifies high-impact publications with an AUROC score of 0.737. Our Manifesting Pipeline also successfully reconstructs core concepts from the latest top-journal articles solely from their keyword sets. An LLM-based scoring system estimates that this reconstruction was sound for over 85% of the cases. Finally, our embedding space analysis shows that outputs from Spacer are significantly more similar to leading publications compared with those from SOTA LLMs.
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。