PaperBridge: Crafting Research Narratives through Human-AI Co-Exploration
summary
Tool that pulls publications from Google Scholar, clusters them with LLMs, and lets users alternate between bi-directional analysis engine top-down intent and bottom-up paper grouping; it encodes narratives in an editable JSON schema, offers four framework patterns (parallel, linear, coordinate, circular), generates contribution statements and slide drafts, and supports locking and iterative edits. Content analysis of 53 HCI talks informs three narrative components, and a user study (N=12) reports low cognitive burden and positive usability for crafting alternative research narratives.
AI-written summary · about
chapters (7)
- 0:00Introduction and motivation
- 1:57Research narrative challenges
- 4:42PaperBridge workflow overview
- 7:55Top-down and bottom-up exploration
- 9:19User study findings
- 10:43Future directions and reflections
- 11:45Q&A session
related talks
35mThe Podcast Pipeline Nobody Sees: Behind the Scenes with AI Agents and AI gen
10mFrom Philosophy to Interfaces: an Explanatory Method and a Tool Inspired by Achinstein's Theory ...
39mNarrative Stress Tests: Designing AI UX That People Trust
10mCrowdsourcing Scholarly Discourse Annotations
25mCrafting your AI play(book)
35mBuilding AI-powered user interfaces
41mThe Role Of Storytelling For UX In The Time Of AI
40mContext That Dreams
