Simiao Ren, Xingyu Shen, Tommy Duong, Ankit Raj · 2026 · arXiv (Cornell University)
DOI: 10.48550/arxiv.2610.30758 · cited by 0 works (OpenAlex) · open-access PDF
La edición asistida por IA puede producir documentos de préstamo que conservan los diseños de emisores familiares mientras cambian la identidad del solicitante. Investigamos si los contratistas experimentados y los procesadores de préstamos identifican tales falsificaciones en el primer paso, la revisión solo de documentos. Tres profesionales reclutados a través de Upwork cada uno recibió un paquete de solicitante extraído de 134 documentos PDF falsos derivados de 47 documentos financieros genuinos suministrados con el consentimiento completo. Las ediciones conservaron cantidades, fechas y saldos; las inconsistencias de identificación introducidas por el tubo fueron conscientemente retenidas antes de la distribución. A los revisores no se les dijo que los archivos habían sido alterados y no se les devolvió ningún juicio a nivel visual. Verificando sus explica
Machine translation (Meta M2M100); the English original follows.
AI-assisted editing can produce loan documents that preserve familiar issuer layouts while changing the applicant's identity. We investigated whether experienced underwriters and loan processors identify such forgeries in first-pass, document-only review. Three practitioners recruited through Upwork each received one applicant package drawn from 134 forged PDFs derived from 47 genuine financial documents supplied with full consent. The edits preserved amounts, dates and balances; identifier inconsistencies introduced by the pipeline were knowingly retained before distribution. Reviewers were not told that files had been altered and returned 132 file-level judgements. Checking their explanations against the originals yielded 14 edit-supported concerns (10.6%): 12 Suspicious judgements and two Insufficient information judgements. All supported concerns involved identifier disagreements within or across documents, and no reported visual cue identified an actual edit. Thus, approximately one in ten judgements contained evidence of the forgery, despite known inconsistencies remaining in the files. These observations motivate evaluating consistency checks and independent source verification alongside human review. With three reviewer-package pairs and no genuine-file controls, the findings describe this exploratory setting rather than population-wide detection accuracy.
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
Topics: Underwriting, Loan, Identifier, Consistency (knowledge bases), Issuer, Actuarial science
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.30758, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange