迈向自动研究：利用具有分类结构的论文知识图谱挖掘可证伪的研究思路
Toward Auto-Research: Mining Falsifiable Research Ideas from Paper Knowledge Graphs with Categorical Structure
浏览论文内容
中文总结 AI 辅助
该研究针对LLMs构建的自动研究思路生成系统的结构缺陷，提出基于范畴论的三层算法，可高效过滤跨领域研究思路候选，兼具高过滤比与高可证伪率，且支持日志记录。
中文摘要 AI 辅助
基于大语言模型（LLMs）构建的自动研究思路生成系统存在共同的结构缺陷：它们将思路生成简化为自由文本重组、随机论文配对或嵌入相似性检索。这三种方法的失效方式相同：均将论文视为扁平对象、字符串或向量，从而忽略了研究人员在进行跨领域类比推理时实际使用的带类型的问题-方法-指标-主张箭头。我们利用仅带类型的图无法提供的范畴论最小单元——合成与恒等箭头，恢复缺失的结构，这使得我们能够探究所提出的类比是否能保留关系链。具体而言，每篇论文$p$被建模为一个小型范畴$C_p$，其对象为提取的带类型研究实体，态射为该论文断言的关系；从$p$到$q$的跨论文桥梁则是一个部分函子候选$F: C_p -> C_q$，它需保留对象种类和覆盖的关系类。我们将该模型实例化为三层算法：范畴签名聚类、函子保留门、以及六轴LLM合理性判断器。在对数万篇经全文解析的论文构成的语料库进行的四项消融实验评估中，该范畴门以约17:1的比例过滤跨领域候选，同时被接受思路的定量可证伪率始终保持在83%以上；每个被拒绝的候选都保留了其各轴的理由，因此该门不仅是静默过滤器，还兼具日志层的功能。
英文摘要
Automated research-idea generation systems built on large language models (LLMs) share a structural weakness: they reduce ideation to free-text recombination, random paper pairing, or embedding-similarity retrieval. The three approaches fail in the same way: each treats a paper as a flat object, a string or a vector, and so quotients away the typed problem-method-metric-claim arrows a researcher actually uses when reasoning about a cross-domain analogy. We recover the missing structure with the minimal piece of category theory that a typed graph alone does not provide: composition, together with identity arrows, which makes it possible to ask whether a proposed analogy preserves relation chains. Concretely, each paper $p$ is modelled as a small category $C_p$ whose objects are extracted typed research entities and whose morphisms are the relations the paper asserts; a cross-paper bridge from $p$ to $q$ is then a partial functor candidate $F: C_p -> C_q$ that preserves object kinds and covered relation classes. We instantiate the model as a three-layer algorithm: categorical signature clustering, a functor-preservation gate, and a six-axis LLM plausibility judge. Evaluated on a corpus of tens of thousands of full-text-parsed papers under four ablation conditions, the categorical gate filters cross-domain candidates at roughly a 17:1 ratio while the quantitative-falsifier rate of accepted ideas stays above 83% throughout; every rejected candidate is retained with its per-axis rationale, so the gate doubles as a logging layer rather than a silent filter.
发表机构
- Sino-German Joint Software Institute（中德软件联合研究所）
- Beihang University（北京航空航天大学）
机构由 AI 辅助整理，请以论文原文为准。
