PapersMulti-sourceSelected

RoPA Manager Automates Vietnam Privacy Compliance Using Local LLMs

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

Why we picked it

The core result is that a quantized local model can match a cloud API on Vietnamese compliance extraction, removing the data-sovereignty objection that blocks LLM use under privacy law. Compliance teams and legal-tech builders in Vietnam face a 1 January 2026 deadline, and this shows a single 24 GB GPU suffices for the workload. The unmeasured value-level precision and mid-range token coverage are caveats to weigh before deployment.

Vietnam's Personal Data Protection Law (Law No.91/2025/QH15) and Decree No.

Body

356/2025/ND-CP take effect on 1 January 2026 and require organizations to maintain Records of Processing Activities (RoPA).

RoPA Manager automates RoPA extraction with hybrid retrieval combining tsvector lexical ranking, dense-vector search and Reciprocal Rank Fusion, paired with locally deployed LLMs.

The authors built a Vietnamese benchmark covering 32 organizations, 77 processing activities, 12 field groups and 4,338 reference values.

End-to-end extraction reached 50.04-55.

25% token coverage against reference labels, and two experts reviewing 1,558 reference values found no incorrect values with 99.

68% agreement (PABAK = 0.9936).

Across 32 paired scenarios on a 24 GB GPU, Qwen3.5-27B-GPTQ-Int4 showed no statistically significant difference from cloud-based DeepSeek-V4-Flash, while Gemma-4-31B performed significantly worse (p < 0.

01).

Original · arXiv: DeepSeek

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

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).

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Papers" desk, focusing on Southeast Asia and the ASEAN-6 (Singapore, Malaysia, Indonesia, Thailand, Vietnam, Philippines) digital economy. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and AI regulation, compliance frameworks, and sovereign compute policy. Key entities and technical topics under continuous tracking include RoPA, Qwen3.5, DeepSeek-V4-Flash, RAG.

Primary source verification: published directly by arXiv: DeepSeek with first-party authority. Cross-source corroboration: 4 independent sources have covered this development (including shao__meng, Harrison Chase, Together AI), confirming industry-wide signal strength.