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).

Seunghoo Lee is a Master's student majoring in AI Imaging at the Graduate School of Advanced Imaging Sciences, Multimedia and Film, Chung-Ang University. His research is primarily focused on the fields of Computer Vision and Natural Language Processing, including projects on sketch image colorization, image generation, image-level anomaly detection, enhancing the reliability of academic information using Large Language Models (LLMs) and multi-agent systems, and designing a framework to evaluate the performance of Small Language Models (SLMs).