Metraipolis › archive › dc_3e2d3fe427f7

BiasMix-Finance: Post-Generation KYC Guardrails for LLM Portfolio Advice — arXiv:2608.28646

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.28646
License (as archived)
CC0-1.0
Archived
2026-10-17T07:41:45.798Z
SHA-256 of the archived text
e1e6a8494eb0b4b92c97b86016b2d562330c12ff412002540799c70ecfda4896
Stable URL of this page
https://metraipolis.com/documento/dc_3e2d3fe427f7

How to cite

BiasMix-Finance: Post-Generation KYC Guardrails for LLM Portfolio Advice — arXiv:2608.28646 — arXiv (en), https://arxiv.org/abs/2608.28646 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3e2d3fe427f7 (Metraipolis archive dc_3e2d3fe427f7, sha256 e1e6a8494eb0b4b92c97b86016b2d562330c12ff412002540799c70ecfda4896)
BibTeX
@misc{dc3e2d3fe427f7,
  title = {BiasMix-Finance: Post-Generation KYC Guardrails for LLM Portfolio Advice — arXiv:2608.28646},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.28646},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3e2d3fe427f7; sha256 e1e6a8494eb0b4b92c97b86016b2d562330c12ff412002540799c70ecfda4896},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28646. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) can generate plausible-sounding ETF portfolios while silently violating basic KYC-style constraints on risk, fees, and diversification. This is especially problematic in agentic multi-turn advisory systems, where each draft recommendation can become an action unless guarded by an auditable enforcement layer. We study a model-agnostic, asset-agnostic post-generation guardrail pipeline: (i) enforce a strict JSON allocation schema, (ii) validate allocations against numeric caps, and (iii) when violations occur, deterministically project the output to the nearest feasible portfolio via a convex quadratic program (QCQP). We introduce BiasMix-Finance (Mini), a compact stress-test benchmark for constrained decision-making under biased LLM generations, with a 16-ETF universe, three investor profiles, and eight bias prompts. Across three models and three inference modes (direct, critique, self-consistency), first-pass generations violate at least one cap in 47.6-85.7% of test cases (67.2% pooled), but the convex projection layer reduces final feasibility violations to 0% while requiring only a small correction distance (test pooled median D=||w*-w0||_2=0.066), indicating that the guardrail typically preserves the intent of the original allocation. We report violation rates and correction distances with confidence intervals, and paired model comparisons with multiple-testing correction. To support reproducibility, we release the dataset, prompts, caps, and code in our public GitHub repository.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.28646 — 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 2026-10-17T07:28:26.468Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).