Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.14607 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913082334248960 |
|---|---|
| author | Nguyen, Ha Thanh Fungwacharakorn, Wachara Wehnert, Sabine Zin, May Myo Kong, Yuntao Xue, Jieying Araszkiewicz, Michał Goebel, Randy Satoh, Ken |
| author_facet | Nguyen, Ha Thanh Fungwacharakorn, Wachara Wehnert, Sabine Zin, May Myo Kong, Yuntao Xue, Jieying Araszkiewicz, Michał Goebel, Randy Satoh, Ken |
| contents | We study the overall process of automatic formalization of GDPR provisions using large language models, within a human-in-the-loop verification framework. Rather than aiming for full autonomy, we adopt a role-specialized workflow in which LLM-based AI components, operating in a multi-agent setting with iterative feedback, generate legal scenarios, formal rules, and atomic facts. This is coupled with independent verification modules which include human reviewers' assessment of representational, logical, and legal correctness. Using this approach, we construct a high-quality dataset to be used for GDPR auto-formalization, and analyze both successful and problematic cases. Our results show that structured verification and targeted human oversight are essential for reliable legal formalization, especially in the presence of legal nuance and context-sensitive reasoning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_14607 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GDPR Auto-Formalization with AI Agents and Human Verification Nguyen, Ha Thanh Fungwacharakorn, Wachara Wehnert, Sabine Zin, May Myo Kong, Yuntao Xue, Jieying Araszkiewicz, Michał Goebel, Randy Satoh, Ken Artificial Intelligence We study the overall process of automatic formalization of GDPR provisions using large language models, within a human-in-the-loop verification framework. Rather than aiming for full autonomy, we adopt a role-specialized workflow in which LLM-based AI components, operating in a multi-agent setting with iterative feedback, generate legal scenarios, formal rules, and atomic facts. This is coupled with independent verification modules which include human reviewers' assessment of representational, logical, and legal correctness. Using this approach, we construct a high-quality dataset to be used for GDPR auto-formalization, and analyze both successful and problematic cases. Our results show that structured verification and targeted human oversight are essential for reliable legal formalization, especially in the presence of legal nuance and context-sensitive reasoning. |
| title | GDPR Auto-Formalization with AI Agents and Human Verification |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2604.14607 |