Photo of Hyeonsu B. Kang
Hyeonsu B. Kang


Main stages of Synergi. (A) A scholar highlights a patch of text in a paper PDF that describes an interesting research problem with references. (B) The system retrieves important papers specifically relevant to the highlighted context in terms of how they have been previously cited by other scholars, via Loopy Belief Propagation over a local 2-hop citation graph from the seed references (Section~
ef{section:retrieval_algorithm}). (C) Relevant text snippets extracted from top-ranked papers are hierarchically structured and recursively summarized using GPT-4 in the chat interface. (D) The outline of threads, supporting citation contexts, and references are presented to the scholar for importing, modifying, and refactoring in the editorEfficiently reviewing scholarly literature and synthesizing prior art are crucial for scientific progress. Yet, the growing scale of publications and the burden of knowledge make synthesis of research threads more challenging than ever. While significant research has been devoted to helping scholars interact with individual papers, building research threads scattered across multiple papers remains a challenge. Most top-down synthesis (and LLMs) make it difficult to personalize and iterate on the output, while bottom-up synthesis is costly in time and effort. Here, we explore a new design space of mixed-initiative workflows. In doing so we develop a novel computational pipeline, Synergi, that ties together user input of relevant seed threads with citation graphs and LLMs, to expand and structure them, respectively. Synergi allows scholars to start with an entire threads-and-subthreads structure generated from papers relevant to their interests, and to iterate and customize on it as they wish. In our evaluation, we find that Synergi helps scholars efficiently make sense of relevant threads, broaden their perspectives, and increases their curiosity. We discuss future design implications for thread-based, mixed-initiative scholarly synthesis support tools.

Synergi Demo Video

Threddy Demo Video

Conference Presentations

coming soon...


Synergi: A Mixed-Initiative System for Scholarly Synthesis and Sensemaking
Hyeonsu B Kang, Sherry Wu, Joseph Chee Chang, A. Kittur. The ACM Symposium on User Interface Software and Technology. 2023.

Threddy: An Interactive System for Personalized Thread-based Exploration and Organization of Scientific Literature
Hyeonsu B Kang, Joseph Chee Chang, Yongsung Kim, A. Kittur. Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology. 2022.