Metraipolis › archive › dc_819d5dfe45be

Spectra: A Rules-Driven LLM Pipeline for Automated KYC Document Processing — arXiv:2609.25474

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.25474
License (as archived)
CC0-1.0
Archived
2026-10-08T13:45:02.097Z
SHA-256 of the archived text
45b2365a945c544c48e4278e2ff6d89212635490563b7a47dd3db08a330584c1
Stable URL of this page
https://metraipolis.com/documento/dc_819d5dfe45be

How to cite

Spectra: A Rules-Driven LLM Pipeline for Automated KYC Document Processing — arXiv:2609.25474 — arXiv (en), https://arxiv.org/abs/2609.25474 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_819d5dfe45be (Metraipolis archive dc_819d5dfe45be, sha256 45b2365a945c544c48e4278e2ff6d89212635490563b7a47dd3db08a330584c1)
BibTeX
@misc{dc819d5dfe45be,
  title = {Spectra: A Rules-Driven LLM Pipeline for Automated KYC Document Processing — arXiv:2609.25474},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.25474},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_819d5dfe45be; sha256 45b2365a945c544c48e4278e2ff6d89212635490563b7a47dd3db08a330584c1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25474. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Know Your Client (KYC) onboarding in capital markets requires analysts to manually classify documents, extract structured data from heterogeneous sources, and validate compliance against complex regulatory policies. This process requires significant analyst time per client, with end-to-end onboarding often stretching to multiple weeks due to sequential handoffs. In this work, we analyze an on-boarding process and find that it comprises repeatable components well-suited to AI automation. We therefore propose a restructured workflow to be amenable to automation: we consolidate the traditional four-party process into two parties that share most of the work and can be automated together, eliminating intermediate handoffs that compound delays. To automate the remaining steps, we introduce Spectra, an AI-assisted document processing platform that combines a structured rules engine with LLM-based classification, extraction, and validation agents. The rules engine encodes compliance policy as a queryable database, enabling focused context injection that reduces token usage while improving extraction precision. Rather than a single monolithic prompt, the system decomposes document processing into isolated, auditable stages, each optimized independently and traceable to specific policy clauses. In evaluation on real KYC documents, Spectra achieves 100% classification accuracy and 89.4% extraction accuracy. Human review burden dropped by 96%.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.25474 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T13:18:38.086Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).