Metraipolis › archive › dc_57315efab35b

Automated Regulatory Compliance Question Answering in Financial Services with Domain-Adapted Retrieval-Augmented Generation — arXiv:2609.30009

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.30009
License (as archived)
CC0-1.0
Archived
2026-10-08T04:27:57.398Z
SHA-256 of the archived text
bb422bf1538636c6a8d0329b2d136dde76805959fc1563881ceaddda904d7907
Stable URL of this page
https://metraipolis.com/documento/dc_57315efab35b

How to cite

Automated Regulatory Compliance Question Answering in Financial Services with Domain-Adapted Retrieval-Augmented Generation — arXiv:2609.30009 — arXiv (en), https://arxiv.org/abs/2609.30009 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_57315efab35b (Metraipolis archive dc_57315efab35b, sha256 bb422bf1538636c6a8d0329b2d136dde76805959fc1563881ceaddda904d7907)
BibTeX
@misc{dc57315efab35b,
  title = {Automated Regulatory Compliance Question Answering in Financial Services with Domain-Adapted Retrieval-Augmented Generation — arXiv:2609.30009},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.30009},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_57315efab35b; sha256 bb422bf1538636c6a8d0329b2d136dde76805959fc1563881ceaddda904d7907},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30009. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Financial institutions operate under dense, frequently amended rulebooks, and answering a compliance question correctly requires not only fluency but verifiable grounding in the authoritative text. Large language models are attractive for this task, yet the models that firms can realistically deploy on-premise are compact ones, and compact models hallucinate obligations. We study whether a carefully domain-adapted retrieval-augmented generation pipeline closes that gap. Our retriever is built in three stages on top of LegalBERT: entailment tuning that recasts question--passage matching as premise--hypothesis reconstruction, contrastive tuning with in-batch negatives, and score-level fusion with BM25. Our generator is a compact model (2B--12B parameters) served under 4-bit quantization, either prompted or adapted with retrieval-aware fine-tuning (RAFT) through LoRA. On ObliQA, a question-answering benchmark built from the Abu Dhabi Global Market rulebooks, the staged retriever raises Recall@10 from 0.256 to 0.774 and outperforms BM25 (0.678) and E5-large-v2 (0.758), the strongest general-purpose dense encoder we tested. RAFT-LoRA then improves the composite RePASs answer-quality score for every model we could adapt, with the largest gain on the weakest one. However, the adapted models do not transfer to Australian case-law questions, and a closed-book model that receives no passages at all scores within 0.011 RePASs of the full pipeline while producing answers that cite nothing and misstate obligations. The retrieval gain is therefore measured directly, the generation gain is a gain in RePASs rather than demonstrated grounding, and grounding itself requires an evaluation protocol that RePASs does not provide.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.30009 — 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 2026-10-08T03:50:58.214Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).