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

Read full text
Authors: Association for Artificial Intelligence 2026, Jooweon Choi, Jinhee Jang, Youngbin Kim, June Hyoung Kwon, Yoonji Lee, SeungHoo Lee, Seunguk Yu, JungMin Yun
Cited by: 0

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).

Fields of Study & Subjects

scientometrics and bibliometrics research Academic Writing and Publishing Software Engineering Research

Publication details

Journal / source
Underline Science Inc.
Publication date
7 January 2026
Language
EN