EUVIMEDEUVIMED entdecken
Crossref

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

SeungHoo Lee, JuneHyoung Kwon, Jooweon Choi, JungMin Yun, Seunguk Yu, Yoonji Lee, Jinhee Jang, YoungBin Kim

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (48) · 41625-41627

DOI: 10.1609/aaai.v40i48.42361 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von SeungHoo Lee und 7 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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).

Zitieren

APA

Lee, S., Kwon, J., Choi, J., Yun, J., Yu, S., Lee, Y., Jang, J., & 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

Vancouver

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

BibTeX
@article{Lee2026,
  author = {Lee, SeungHoo and Kwon, JuneHyoung and Choi, Jooweon and Yun, JungMin and Yu, Seunguk and Lee, Yoonji and Jang, Jinhee and Kim, YoungBin},
  title = {RefLens: End-to-End Evidence-Grounded Citation Verification with LLM Agents},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {48},
  pages = {41625--41627},
  doi = {10.1609/aaai.v40i48.42361}
}
Kostenlos starten →