EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Trust Triangle: A Reliability-Validity-Generation Framework for Explainable Credit Card Fraud Detection with RAG-Enhanced LLMs Reasoning

Jin-Ching Shen, Nai-Ching Su, Yi-Bing Lin

AI · 19.03.2026 · 7 (3) · 114

DOI: 10.3390/ai7030114 ↗

Kurz gefasst

Fachartikel in der Zeitschrift AI, online erschienen am 19.03.2026. Verfasst von Jin-Ching Shen und 2 weiteren Autor:innen. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We propose Trust Triangle, a Bridging Methodology that establishes evidential reliability through multi-attribution consensus, ensures external validity via statistical hypothesis testing, and enables controlled generation with RAG-anchored LLMs to transform black-box predictions into trustworthy, auditable explanations. This framework is instantiated for credit card fraud detection by integrating multi-method feature attributions with rigorous statistical validation. The resulting reliability-validity-verified insights are synthesized with high-relevance domain knowledge (relevance score > 0.7) retrieved from a real-world corpus via Retrieval-Augmented Generation (RAG). A structured Chain-of-Thought (CoT) prompt then guides an LLM to produce coherent, audit-ready case reports. Our contributions are threefold: (1) a verifiable framework for quantifying attribution reliability and validity, (2) a demonstrated end-to-end pipeline from robust prediction to semantically grounded explanation, and (3) a generalizable paradigm for Trustworthy ML in high-stakes domains. Experiments on a highly imbalanced dataset (fraud rate: 8.74%) demonstrate robust performance (PR-AUC = 0.7867), successfully identify statistically significant predictive features, and generate audit-ready reports, thereby advancing a rigorous, evidence-based pathway from model output to decision-ready support.

Zitieren

APA

Shen, J., Su, N., & Lin, Y. (2026). Trust Triangle: A Reliability-Validity-Generation Framework for Explainable Credit Card Fraud Detection with RAG-Enhanced LLMs Reasoning. AI, 7(3), 114. https://doi.org/10.3390/ai7030114

Vancouver

Shen J, Su N, Lin Y. Trust Triangle: A Reliability-Validity-Generation Framework for Explainable Credit Card Fraud Detection with RAG-Enhanced LLMs Reasoning. AI. 2026;7(3):114. doi:10.3390/ai7030114

BibTeX
@article{Shen2026,
  author = {Shen, Jin-Ching and Su, Nai-Ching and Lin, Yi-Bing},
  title = {Trust Triangle: A Reliability-Validity-Generation Framework for Explainable Credit Card Fraud Detection with RAG-Enhanced LLMs Reasoning},
  journal = {AI},
  year = {2026},
  volume = {7},
  number = {3},
  pages = {114},
  doi = {10.3390/ai7030114}
}
Kostenlos starten →