Asterism：将散落观察综合为有文献依据的假设与理论
Asterism: Exploring and Synthesizing Scattered Observations into Literature-Grounded Hypotheses and Theories
研究团队提出 Asterism，从数百篇论文中抽取概念-关系三元组，并用层级本体统一概念，让研究者通过证据图在不同粒度上聚合观察、自主构建理论。在 n=10 的实地部署中，研究者从观察推进到理论并保留符合自身偏好的概念与假设；免疫学和农业两个案例研究团队还发现了常规分析之外的机制，并提出值得后续实验验证的假设。
Authors:Joseph Chee Chang, Michael D'Arcy, Amy X. Zhang, Pao Siangliulue, Sangho Suh, Aakanksha Naik, Jena D. Hwang, Javier Ramos Benitez, Stella Wroblewski, Matt Latzke, Michael Cuoco, Ruben Lozano-Aguilera, Kris Ganjam, Joel Chan, Doug Downey, Peter Jansen, Kyle J. Travaglini, Daniel S. Weld
Abstract:A theory draws many independent observations into one framework with novel hypotheses. A researcher building such a theory must synthesize observations scattered across many papers, each describing related concepts but often in different terms. Which concepts matter most also depends on their preferences and research questions. Recent approaches scale theory synthesis with LLMs, but automate away choices and intuitions from researchers. We present Asterism, which extracts observations from hundreds of papers as concept-relation triples, with concepts unified in a hierarchical ontology. Researchers curate an evidence graph using the ontology and aggregate observations at different levels of granularity to focus theory formation on specific phenomena of interest. In a field deployment (n=10), researchers worked from observations to theories, and kept concepts and hypotheses fitting their preferences. In two case studies, teams of immunology and agriculture researchers discovered mechanisms outside their standard analyses and constructed hypotheses worth follow-up experiments.
| Subjects: | Human-Computer Interaction (cs.HC); Computation and Language (cs.CL); Digital Libraries (cs.DL); Information Retrieval (cs.IR) |
| Cite as: | arXiv:2610.02673 [cs.HC] |
| (or arXiv:2610.02673v1 [cs.HC] for this version) | |
| https://doi.org/10.48550/arXiv.2610.02673 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Joseph Chee Chang [view email]
[v1]
Fri, 2 Oct 2026 01:55:14 UTC (4,122 KB)
来源：arXiv：cs.CL · arxiv.org