AIC CTU@FEVER 8: On-premise fact checking through long context RAG

Herbert Ullrich, Jan Drchal


Abstract
In this paper, we present our fact-checking pipeline which has scored first in FEVER 8 shared task. Our fact-checking system is a simple two-step RAG pipeline based on our last year’s submission. We show how the pipeline can be redeployed on-premise, achieving state-of-the-art fact-checking performance (in sense of Ev2R test-score), even under the constraint of a single Nvidia A10 GPU, 23GB of graphical memory and 60s running time per claim.
Anthology ID:
2025.fever-1.22
Volume:
Proceedings of the Eighth Fact Extraction and VERification Workshop (FEVER)
Month:
July
Year:
2025
Address:
Vienna, Austria
Editors:
Mubashara Akhtar, Rami Aly, Christos Christodoulopoulos, Oana Cocarascu, Zhijiang Guo, Arpit Mittal, Michael Schlichtkrull, James Thorne, Andreas Vlachos
Venues:
FEVER | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
274–280
Language:
URL:
https://preview.aclanthology.org/acl25-workshop-ingestion/2025.fever-1.22/
DOI:
Bibkey:
Cite (ACL):
Herbert Ullrich and Jan Drchal. 2025. AIC CTU@FEVER 8: On-premise fact checking through long context RAG. In Proceedings of the Eighth Fact Extraction and VERification Workshop (FEVER), pages 274–280, Vienna, Austria. Association for Computational Linguistics.
Cite (Informal):
AIC CTU@FEVER 8: On-premise fact checking through long context RAG (Ullrich & Drchal, FEVER 2025)
Copy Citation:
PDF:
https://preview.aclanthology.org/acl25-workshop-ingestion/2025.fever-1.22.pdf