基于长上下文RAG的本地化事实核查，单卡60秒内达顶尖性能。
AIC CTU@FEVER 8: On-premise fact checking through long context RAG
- 两步RAG流水线，利用长上下文增强检索与推理
- 在单张A10 GPU上实现Ev2R得分领先，耗时不超过60秒
- 可本地部署，适合对数据隐私要求高的场景
本文介绍我们在FEVER 8共享任务中获得第一名的事实核查系统。该系统是一个基于去年提交方案的简单两步RAG流水线。我们展示了该流程如何在本地部署，即使受限于单张NVIDIA A10 GPU、23GB显存和每条声明最多60秒运行时间，仍能实现最先进的事实核查性能（以Ev2R测试得分衡量）。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。