让人类与大模型协作，用论文要素重组生成新科研创意。
Human-LLM Compound System for Scientific Ideation through Facet Recombination and Novelty Evaluation
- 从论文中提取目的、机制、评价等要素，交互式重组生成新想法。
- 用户研究显示，系统在创意探索和表达力上显著优于基线方法。
- 通过要素化新颖性验证，帮助判断创意是否真正创新。
科学创意生成常依赖于对已有论文要素的融合。我们提出Scideator，首个基于要素的「人-大模型」协同科研创意系统。用户输入论文后，系统自动提取其及关联论文中的关键要素（目的、机制、评估），支持用户交互式重组以生成新想法。系统包含三大设计：（1）人机协同要素重组，通过「要素化创意生成器」模块寻找跨论文的类比关系；（2）距离可控检索，由「类比论文要素查找器」模块返回从同主题到完全不同领域的一系列参考论文，拓展思路范围；（3）基于要素的新颖性验证，通过「创意新颖性检查器」模块实现「检索-重排序」流程，利用要素评估创意原创性。在计算机科学研究人员的用户研究中，相较仅使用相同基础大模型但无要素模块的基线，Scideator在创意探索与表达性方面表现更优。消融实验表明，要素化检索-重排序比标准方法发现更相关论文，基于要素的新颖性分类器也优于基于非结构化文本的分类器。
原文摘要 · Abstract (English)
The scientific ideation process often involves blending facets of existing papers to create new ideas. We contribute Scideator, the first human-LLM system for facet-based scientific ideation. Starting from user-provided papers, Scideator extracts key facets -- purposes, mechanisms, and evaluations -- from these and related papers, allowing users to interactively recombine facets to synthesize ideas. Scideator is driven by three design choices: (1) human-in-the-loop facet recombination, in which users select facets from retrieved papers and the system generates ideas by finding analogies across them via the Faceted Idea Generator module; (2) distance-controlled retrieval via the Analogous Paper Facet Finder module, which surfaces papers ranging from the same topic to entirely different areas to provide a spectrum of directions; and (3) facet-based novelty verification via the Idea Novelty Checker module, a retrieve-then-rerank pipeline that helps users to evaluate idea originality using facets. In a user study with computer science researchers, Scideator provided significantly more creativity support than a baseline using the same backbone LLM without our facet-based modules, particularly in idea exploration and expressiveness. Ablations further show that the facets benefit the novelty checker: facet-based retrieve-then-rerank surfaces more relevant papers than standard retrieval and re-ranking, and a facet-grounded novelty classifier outperforms classifiers that reason over unstructured ideas and papers.
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。