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

  • Runhua ZHANG
  • , Yang OUYANG
  • , Leixian SHEN
  • , Yuying TANG
  • , Xiaojuan MA
  • , Huamin QU
  • , Xian XU*
  • *Corresponding author for this work

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Referred Conference Paperpeer-review

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.
Original languageEnglish
Title of host publicationUIST 2025: Proceedings of the 38th Annual ACM Symposium on User Interface Software and Technology
EditorsAndrea BIANCHI, Elena GLASSMAN, Wendy E. MACKAY, Shengdong ZHAO, Jeeeun KIM, Ian OAKLEY
PublisherAssociation for Computing Machinery, Inc
Pages1-21
ISBN (Print)9798400720376
DOIs
Publication statusPublished - Sept 2025
EventThe 38th Annual ACM Symposium on User Interface Software and Technology - Busan, Korea, Republic of
Duration: 28 Sept 20251 Oct 2025

Conference

ConferenceThe 38th Annual ACM Symposium on User Interface Software and Technology
Abbreviated titleUIST '25
Country/TerritoryKorea, Republic of
CityBusan
Period28/09/251/10/25

Bibliographical note

We sincerely thank all participants for their time and efforts, and
the anonymous reviewers for their constructive feedback, which significantly improved the quality of this paper.

We would like to thank Dr. Chengbo Zheng and Liwenhan Xie for their valuable discussions during the revision of this paper. We also thank Junze Li, Dr. Yao Wang, Hanlu Ma, Dr. Linping Yuan, Dingdong Liu, and Zheng Wei for their insightful comments on earlier drafts, and Jiawen Liu and Meiying Li for their help with proofreading. Finally, the first author wishes to express special thanks to Dr. Yulin Tian, Ziqi Pan, Qiaoyi Chen, and to those who showed patience and support during a personally challenging time. Their encouragement and willingness to simply be there made it possible to carry this work through to completion.

Publisher Copyright:
© 2025 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

Funding

This work was partially supported by RGC GRF grant 16210722, and was supported in part by the EdUHK-HKUST Joint Centre for Artificial Intelligence (JC_AI) research scheme: Grant No. FB454.

Keywords

  • Academic Communication
  • Human-AI Collaboration
  • Storytelling

Fingerprint

Dive into the research topics of 'PaperBridge: Crafting Research Narratives through Human-AI Co-Exploration'. Together they form a unique fingerprint.

Cite this