Reproduce “PaperBridge: Crafting Research Narratives through Human-AI Co-Exploration” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Runhua Zhang, Yang Ouyang, Leixian Shen, Yuying Tang, Xiaojuan Ma, Huamin Qu, Xian Xu
A human-AI co-exploration system, PaperBridge, assists researchers in structuring and articulating narratives from their published work, moving beyond quantitative metrics to content-driven storytelling. It demonstrates excellent usability and helps users efficiently explore diverse perspectives for their research, fostering new insights into their scholarly contributions.
Key insights
- Academic storytelling relies on three core elements: a narrative framework, a defined perspective (contribution statement and clusters), and a justifying rationale.
- Four distinct narrative frameworks (Parallel, Linear, Coordinate, Circular) and rhetorical strategies (Ethos, Pathos, Logos) effectively structure and articulate research narratives.
- Human-AI co-exploration, leveraging LLMs to generate 'sparks' and enabling iterative refinement, aids researchers in discovering new perspectives on their own work and fostering deeper reflection.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.