RefLens: End-to-End Evidence-Grounded Citation Verification with LLM Agents

Authors

  • SeungHoo Lee Chung-Ang University
  • JuneHyoung Kwon Chung-Ang University
  • Jooweon Choi Chung-Ang University
  • JungMin Yun Chung-Ang University
  • Seunguk Yu Chung-Ang University
  • Yoonji Lee Chung-Ang University
  • Jinhee Jang Chung-Ang University
  • YoungBin Kim Chung-Ang University

DOI:

https://doi.org/10.1609/aaai.v40i48.42361

Abstract

Accurate citation is critical, yet error rates remain high across scientific literature. We present RefLens, an end-to-end system that automates citation verification from PDF parsing to interactive report generation. Unlike summary- or embedding-based approaches, RefLens performs evidence-grounded verification by extracting verbatim spans from original sources and displaying citation-level cards and a paper-level dashboard. In a 35-participant study, users rated value (M=4.34), trust (M=4.15), and usability (M=4.19) highly, with strong adoption intention (M=4.28).
AAAI-26 / IAAI-26 / EAAI-26 Proceedings Cover

Downloads

Published

2026-03-14

How to Cite

Lee, S., Kwon, J., Choi, J., Yun, J., Yu, S., Lee, Y., … Kim, Y. (2026). RefLens: End-to-End Evidence-Grounded Citation Verification with LLM Agents. Proceedings of the AAAI Conference on Artificial Intelligence, 40(48), 41625–41627. https://doi.org/10.1609/aaai.v40i48.42361

Issue

Vol. 40 No. 48: EAAI-26 AI for Education, Model AI Assignments, AAAI-26 Emerging Trends, Doctoral Consortium, Student Abstracts, Undergraduate Consortium and Demonstrations

Section

AAAI Demonstration Track