SciNumQA: A Benchmark for Complex Numerical Reasoning Over Scientific Tables
IEEE Access · 2026 · 14 · 82812-82822
DOI: 10.1109/access.2026.3697546 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Sohyun Son und 4 weiteren Autor:innen. Die Arbeit nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Brain Korea 21 (BK21) FOUR, Korean Southeast Center for the 4th Industrial Revolution Leader Education, Institute of Information and Communications Technology Planning and Evaluation (IITP) through the Artificial Intelligence Convergence Innovation Human Resource…, Korean Government [Ministry of Science and ICT (MSIT)].
Abstract (Originalsprache)
Kein Abstract verfügbar.
Förderung
- Brain Korea 21 (BK21) FOUR, Korean Southeast Center for the 4th Industrial Revolution Leader Education
- Institute of Information and Communications Technology Planning and Evaluation (IITP) through the Artificial Intelligence Convergence Innovation Human Resource…
- Korean Government [Ministry of Science and ICT (MSIT)]
- IITP-Information Technology Research Center (ITRC) grant
- Korean Government
- Pusan National University–LG Electronics Smart Control Center
- Korea Health Technology Research and Development Project through Korea Health Industry Development Institute
- Ministry of Health and Welfare, Republic of Korea
Zitieren
APA
Son, S., Kim, Y., Kim, G., Choi, D., & Sung, M. (2026). SciNumQA: A Benchmark for Complex Numerical Reasoning Over Scientific Tables. IEEE Access, 14, 82812-82822. https://doi.org/10.1109/access.2026.3697546
Vancouver
Son S, Kim Y, Kim G, Choi D, Sung M. SciNumQA: A Benchmark for Complex Numerical Reasoning Over Scientific Tables. IEEE Access. 2026;14:82812-82822. doi:10.1109/access.2026.3697546
BibTeX
@article{Son2026,
author = {Son, Sohyun and Kim, Yubin and Kim, Gangwoo and Choi, Donghee and Sung, Mujeen},
title = {SciNumQA: A Benchmark for Complex Numerical Reasoning Over Scientific Tables},
journal = {IEEE Access},
year = {2026},
volume = {14},
pages = {82812--82822},
doi = {10.1109/access.2026.3697546}
}
EUVIMED