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

  • Lee, SeungHoo
  • Kwon, JuneHyoung
  • Choi, Jooweon
  • Yun, JungMin
  • Yu, Seunguk
  • ... Kim, YoungBin
  • 외 2명
Citations

WEB OF SCIENCE

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 paperlevel 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). Project Page- https://hoohahabighead.github.io/RefLens Code- https://github.com/hoohahaBIGHEAD/RefLens-app

제목
RefLens: End-to-End Evidence-Grounded Citation Verification with LLM Agents
저자
Lee, SeungHooKwon, JuneHyoungChoi, JooweonYun, JungMinYu, SeungukLee, YoonjiJang, JinheeKim, YoungBin
DOI
10.1609/aaai.v40i48.42361
발행일
2026
유형
Proceedings Paper
저널명
FORTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE
40
48
페이지
41625 ~ 41627