Metraipolis › archive › dc_45eb48e48e23
CLAIR-Fin: An Adversarial Multi-Agent Framework for Claim-Level Verification and Adaptive Debate in Cross-Modal Financial QA — arXiv:2608.13706
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.13706
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T02:21:03.254Z
- SHA-256 of the archived text
0e72d03852f36ff134da8cd3623ebd693b5e6d8ddb883d2cc8096ac95355b820- Stable URL of this page
https://metraipolis.com/documento/dc_45eb48e48e23
How to cite
CLAIR-Fin: An Adversarial Multi-Agent Framework for Claim-Level Verification and Adaptive Debate in Cross-Modal Financial QA — arXiv:2608.13706 — arXiv (en), https://arxiv.org/abs/2608.13706 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_45eb48e48e23 (Metraipolis archive dc_45eb48e48e23, sha256 0e72d03852f36ff134da8cd3623ebd693b5e6d8ddb883d2cc8096ac95355b820)
BibTeX
@misc{dc45eb48e48e23,
title = {CLAIR-Fin: An Adversarial Multi-Agent Framework for Claim-Level Verification and Adaptive Debate in Cross-Modal Financial QA — arXiv:2608.13706},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.13706},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_45eb48e48e23; sha256 0e72d03852f36ff134da8cd3623ebd693b5e6d8ddb883d2cc8096ac95355b820},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13706. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Existing defenses against hallucination in retrieval-augmented and multi-agent pipelines remain partial: evidence is trusted despite modality disagreement, debate verifies an aggregate report rather than individual claims, and such verification occurs only after drafting, leaving inter-agent errors undetected until the final text. To close this gap, we present CLAIR-Fin, a nine-agent framework that decomposes each question into atomic claims maintained in a typed Financial Claim Ledger. Each claim is resolved through Asymmetric Evidence Authority, which conditions evidence trust on claim type rather than treating all modalities as equally reliable; Chain-of-Custody Verification, which checks grounding at the hand-off between drafting and adversarial review rather than only at the pipeline's exit; an Adaptive Rebuttal Cycle, which routes contested claims through adversarial debate whose depth scales with what that debate finds; and a terminal entailment audit paired with a continuous Hallucination Risk Index that distinguishes claims that passed scrutiny from claims never contested. We evaluate CLAIR-Fin on BB-FinQA-X, a 500-question cross-modal financial evaluation set built from Bangladesh Bank Annual Report material, stratified by query type, format, and difficulty. Relative to a single-pass retrieval-augmented generation baseline, it raises faithfulness ($0.780 \rightarrow 0.889$) while abstaining on 5.4% of questions when evidence is insufficient rather than forcing an unsupported response, and it exceeds stronger retrieval-strategy baselines such as HyDE and Graph-RAG on faithfulness ($\leq 0.874$). Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-17 in cs.AI). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.13706 — 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 2026-10-19T02:02:02.858Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).