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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Ullrich, Herbert, Drchal, Jan
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916883951779840
author Ullrich, Herbert
Drchal, Jan
author_facet Ullrich, Herbert
Drchal, Jan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_04390
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AIC CTU@FEVER 8: On-premise fact checking through long context RAG
Ullrich, Herbert
Drchal, Jan
Computation and Language
Artificial Intelligence
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.
title AIC CTU@FEVER 8: On-premise fact checking through long context RAG
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2508.04390