Synergi: A Mixed-Initiative System for Scholarly Synthesis and Sensemaking
TLDRA novel computational pipeline is developed that ties together user input of relevant seed threads with citation graphs and LLMs, to expand and structure them, respectively, and is found to help scholars efficiently make sense of relevant threads, broaden their perspectives, and increases their curiosity.
How do people cite this paper?
(generated 20 days ago)Synergi has informed the design of subsequent AI-powered scholarly tools by introducing a mixed-initiative workflow combining citation graphs with LLMs for thread-based literature synthesis, and has been cited as a representative system for LLM-supported sensemaking, as a model for combining top-down and bottom-up synthesis strategies in literature review interfaces, as an example of human-AI complementarity in cognitively demanding tasks, and as a methodological reference for evaluation instruments and study designs in sensemaking research.