Metraipolis › archive › dc_c85afb0e024f

FRAUDSkill: Structured Frozen-Weight Skill Optimization for Audio Anti-Fraud Detection — arXiv:2609.18766

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.18766
License (as archived)
CC0-1.0
Archived
2026-10-15T13:50:00.944Z
SHA-256 of the archived text
3b7eea41f32dbe49a256ed4c465f976156f9de09828ea320866f04914255b495
Stable URL of this page
https://metraipolis.com/documento/dc_c85afb0e024f

How to cite

FRAUDSkill: Structured Frozen-Weight Skill Optimization for Audio Anti-Fraud Detection — arXiv:2609.18766 — arXiv (en), https://arxiv.org/abs/2609.18766 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c85afb0e024f (Metraipolis archive dc_c85afb0e024f, sha256 3b7eea41f32dbe49a256ed4c465f976156f9de09828ea320866f04914255b495)
BibTeX
@misc{dcc85afb0e024f,
  title = {FRAUDSkill: Structured Frozen-Weight Skill Optimization for Audio Anti-Fraud Detection — arXiv:2609.18766},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.18766},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c85afb0e024f; sha256 3b7eea41f32dbe49a256ed4c465f976156f9de09828ea320866f04914255b495},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.18766. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large audio-language models have shown promise for anti-fraud detection by directly processing speech and reasoning over fraud-related evidence. Their deployment, however, requires predictions to follow a predefined label space and a structured decision protocol consisting of service-scenario identification, fraud detection, and conditional fraud-type classification. Existing fine-tuning and prompt-based approaches typically encode task knowledge, constraints, and decision rules into model parameters or manually maintained prompts, making them difficult to adapt as fraud patterns and labeling policies evolve. To this end, we propose FRAUDSkill, a structured frozen-weight adaptation framework that leaves the underlying audio-language model unchanged while optimizing an external layer of skill programs, route-specific policies, and decision rules. We further combine structured output control with validation-guided multi-path inference to ensure protocol-compliant predictions. On the TeleAntiFraud benchmark, FRAUDSkill achieves 73.50% Macro-F1, outperforming the shared frozen-model baseline by 31.96% while reducing invalid outputs to 1.94%. Extensive experiments demonstrate that external skill optimization provides an effective and adaptable solution for structured audio anti-fraud detection without modifying the underlying model. The source code is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-17 in cs.CL).
Categorie arXiv: Sound (cs.SD) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.18766 — 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 2026-10-15T13:48:24.435Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).