RefLens: End-to-End Evidence-Grounded Citation Verification with LLM Agents
  • Lee, Seung Hoo
  • Kwon, June Hyoung
  • Choi, Jooweon
  • Yun, Jung Min
  • Yu, Seunguk
  • ... Kim, Young Bin
  • 외 2명
Citations

WEB OF SCIENCE

0
Citations

SCOPUS

0

초록

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).

제목
RefLens: End-to-End Evidence-Grounded Citation Verification with LLM Agents
저자
Lee, Seung HooKwon, June HyoungChoi, JooweonYun, Jung MinYu, SeungukLee, YoonjiJang, JinheeKim, Young Bin
DOI
10.1609/aaai.v40i48.42361
발행일
2026
유형
Conference Paper
저널명
Proceedings of the AAAI Conference on Artificial Intelligence
40
48
페이지
41625 ~ 41627