AIC CTU@FEVER 8: On-premise fact checking through long context RAG
This work addresses efficient, on-premise fact-checking for applications requiring privacy or resource constraints, though it is incremental as it builds on a previous year's submission.
The authors tackled the problem of fact-checking by developing an on-premise two-step RAG pipeline that achieved first place in the FEVER 8 shared task, scoring state-of-the-art performance with constraints of a single NVidia A10 GPU, 23GB memory, and 60s runtime per claim.
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.