mlsanityData to 7 Oct 2026

Automated Extraction of Records of Processing Activities (RoPA) Using Hybrid RAG and Locally Deployed Large Language Models

arXiv 2609.27359 ↗First posted 23 Sep 2026cs.CL cs.CR cs.IRcited by 0

Not on the map. Why?

Abstract (arXiv)

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).

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 10 of its 26 references that are in the map. First posted on arXiv 23 Sep 2026.

Builds on

10 of 26 references.

References · 10

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2017On Calibration of Modern Neural Networkscited by 4,860
  4. 2016Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphscited by 853
  5. 2023Ragas: Automated Evaluation of Retrieval Augmented Generationcited by 408
  6. 2024Multilingual E5 Text Embeddings: A Technical Reportcited by 357
  7. 2023Benchmarking Large Language Models in Retrieval-Augmented Generationcited by 307
  8. 2021LexGLUE: A Benchmark Dataset for Legal Language Understanding in Englishcited by 302
  9. 2020PhoBERT: Pre-trained language models for Vietnamesecited by 148
  10. 2024Seven Failure Points When Engineering a Retrieval Augmented Generation Systemcited by 138

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Optimizing Legal Document Retrieval in Vietnamese with Semi-Hard Negative Mining
  2. 2023Preserving Knowledge Invariance: Rethinking Robustness Evaluation of Open Information Extraction
  3. 2025Transparent NLP: Using RAG and LLM Alignment for Privacy Q&A
  4. 2026Evaluating Structured Information Extraction with Open Models in a High Risk Public Sector Application
  5. 2025Retrieval Models Aren't Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models
  6. 2025Advancing Vietnamese Information Retrieval with Learning Objective and Benchmark
  7. 2026RAGAL: A Frugal, Fully Local Retrieval-Augmented Assistant for Technical Support at a Government Agency
  8. 2024Retrieval Augmented Instruction Tuning for Open NER with Large Language Models