AIC CTU@FEVER 8: On-premise fact checking through long context RAG
About
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.
Herbert Ullrich, Jan Drchal• 2025
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Multimodal Claim Verification | AVerImaTeC (dev) | Q-Eval82.2 | 4 | |
| Verdict Prediction | AVerImaTeC official (test) | Q-Eval80.7 | 4 |
Showing 2 of 2 rows