PaperBridge: Crafting Research Narratives through Human-AI Co-Exploration

TL;DR

PaperBridge is a human-AI system that helps researchers craft coherent research narratives by exploring diverse organizational perspectives, leveraging large language models for iterative, bi-directional analysis.

Contribution

This work introduces PaperBridge, a novel AI-assisted system for organizing research publications into narratives, supported by a formative study and empirical user evaluation.

Findings

Demonstrated usability and effectiveness of PaperBridge in research narrative exploration

Provided empirical insights into interactive systems supporting academic communication

Showed how bi-directional analysis enhances narrative coherence

Abstract

Researchers frequently need to synthesize their own publications into coherent narratives that demonstrate their scholarly contributions. To suit diverse communication contexts, exploring alternative ways to organize one's work while maintaining coherence is particularly challenging, especially in interdisciplinary fields like HCI where individual researchers' publications may span diverse domains and methodologies. In this paper, we present PaperBridge, a human-AI co-exploration system informed by a formative study and content analysis. PaperBridge assists researchers in exploring diverse perspectives for organizing their publications into coherent narratives. At its core is a bi-directional analysis engine powered by large language models, supporting iterative exploration through both top-down user intent (e.g., determining organization structure) and bottom-up refinement on narrative components (e.g., thematic paper groupings). Our user study (N=12) demonstrated PaperBridge's usability and effectiveness in facilitating the exploration of alternative research narratives. Our findings also provided empirical insights into how interactive systems can scaffold academic communication tasks.