CHIMERA: A Knowledge Base of Scientific Idea Recombinations for Research Analysis and Ideation
This work addresses the need for large-scale tools to study and foster cross-disciplinary scientific ideation, though it is incremental as it builds on existing information extraction and language model techniques.
The authors tackled the problem of analyzing and generating scientific innovation by creating CHIMERA, a knowledge base of over 28K recombination examples mined from AI literature, which enables empirical analysis and training models that propose novel research directions rated as inspiring by researchers.
A hallmark of human innovation is recombination -- the creation of novel ideas by integrating elements from existing concepts and mechanisms. In this work, we introduce CHIMERA, a large-scale Knowledge Base (KB) of over 28K recombination examples automatically mined from the scientific literature. CHIMERA enables large-scale empirical analysis of how scientists recombine concepts and draw inspiration from different areas, and enables training models that propose novel, cross-disciplinary research directions. To construct this KB, we define a new information extraction task: identifying recombination instances in scientific abstracts. We curate a high-quality, expert-annotated dataset and use it to fine-tune a large language model, which we apply to a broad corpus of AI papers. We showcase the utility of CHIMERA through two applications. First, we analyze patterns of recombination across AI subfields. Second, we train a scientific hypothesis generation model using the KB, showing that it can propose novel research directions that researchers rate as inspiring. We release our data and code at https://github.com/noy-sternlicht/CHIMERA-KB.