利用混合RAG和本地部署大型语言模型自动化提取处理活动记录（RoPA）

arXiv cs.CL 论文
automated-extraction ropa hybrid-rag locally-deployed-llm personal-data-protection benchmark nlp

摘要

本文提出RoPA Manager，一个使用混合检索和本地部署大型语言模型的自动化系统，用于提取处理活动记录，并在越南语基准上进行了评估。

arXiv:2609.27359v1 Announce Type: new Abstract: Vietnam's Personal Data Protection Law (Law No. 91/2025/QH15) and Decree No. 356/2025/ND-CP, effective January 1, 2026, require organizations to establish and maintain Records of Processing Activities (RoPA). Manual RoPA preparation is labor-intensive, while cloud-hosted large language models (LLMs) may conflict with data-sovereignty requirements. We propose RoPA Manager, a system for automated RoPA information extraction using hybrid retrieval that combines lexical ranking over tsvector, dense-vector search, Reciprocal Rank Fusion (RRF), and locally deployed LLMs. We introduce a Vietnamese RoPA benchmark with 32 organizations, 77 processing activities, 12 field groups, and 4,338 reference values. Evaluation is reported at three distinct levels. The automated scorer, tested on perturbed data without invoking an LLM, achieved F1 = 0.9493 [0.9436, 0.9548]; this measures scorer robustness rather than end-to-end extraction accuracy. End-to-end extraction achieved token coverage of 50.04-55.25% against the reference labels. Two independent experts reviewed 1,558 reference values (35.9% of the benchmark), found no incorrect values, and achieved 99.68% agreement with PABAK = 0.9936. Value-level precision was not measured. Across 32 paired scenarios on a 24 GB GPU, locally deployed Qwen3.5-27B-GPTQ-Int4 showed no statistically significant difference from cloud-based DeepSeek-V4-Flash (difference 0.20 percentage points in favor of DeepSeek, 95% CI [-0.93, 1.32], p = 0.72), while Gemma-4-31B performed significantly worse (p < 0.01).
查看原文
查看缓存全文

缓存时间: 2026/09/24 09:19 

# Automated Extraction of Records of Processing Activities (RoPA) Using Hybrid RAG and Locally Deployed Large Language Models
Source: [https://arxiv.org/abs/2609.27359](https://arxiv.org/abs/2609.27359)
[View PDF](https://arxiv.org/pdf/2609.27359)

> Abstract:Vietnam's Personal Data Protection Law \(Law No\. 91/2025/QH15\) and Decree No\. 356/2025/ND\-CP, effective January 1, 2026, require organizations to establish and maintain Records of Processing Activities \(RoPA\)\. Manual RoPA preparation is labor\-intensive, while cloud\-hosted large language models \(LLMs\) may conflict with data\-sovereignty requirements\. We propose RoPA Manager, a system for automated RoPA information extraction using hybrid retrieval that combines lexical ranking over tsvector, dense\-vector search, Reciprocal Rank Fusion \(RRF\), and locally deployed LLMs\. We introduce a Vietnamese RoPA benchmark with 32 organizations, 77 processing activities, 12 field groups, and 4,338 reference values\. Evaluation is reported at three distinct levels\. The automated scorer, tested on perturbed data without invoking an LLM, achieved F1 = 0\.9493 \[0\.9436, 0\.9548\]; this measures scorer robustness rather than end\-to\-end extraction accuracy\. End\-to\-end extraction achieved token coverage of 50\.04\-55\.25% against the reference labels\. Two independent experts reviewed 1,558 reference values \(35\.9% of the benchmark\), found no incorrect values, and achieved 99\.68% agreement with PABAK = 0\.9936\. Value\-level precision was not measured\. Across 32 paired scenarios on a 24 GB GPU, locally deployed Qwen3\.5\-27B\-GPTQ\-Int4 showed no statistically significant difference from cloud\-based DeepSeek\-V4\-Flash \(difference 0\.20 percentage points in favor of DeepSeek, 95% CI \[\-0\.93, 1\.32\], p = 0\.72\), while Gemma\-4\-31B performed significantly worse \(p < 0\.01\)\.

## Submission history

From: Khuong Nguyen\-An \[[view email](https://arxiv.org/show-email/f5d87041/2609.27359)\] **\[v1\]**Wed, 23 Sep 2026 04:55:53 UTC \(589 KB\)

相似文章

用于模式约束临床信息抽取的检索增强型大语言模型

arXiv cs.CL

本文提出了一种模块化的检索增强生成（RAG）流水线，用于从护理人员与患者的对话转录中提取结构化临床观察结果，采用模式约束提示和第二遍审核，基于Llama和GPT骨干模型，取得了80.36%的F1分数。