# FAA Framework: A Large Language Model-Based Approach for Credit Card Fraud Investigations

arXiv: https://arxiv.org/abs/2506.11635 · HTML: https://mlsanity.com/paper/2506.11635/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 71 references that are in the map.
- First posted on arXiv 13 Jun 2025.

## Builds on (most cited first, 11 of 11)

- [RouteLLM: Learning to Route LLMs with Preference Data](https://mlsanity.com/paper/2406.18665/) (2024)
- [Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing](https://mlsanity.com/paper/2404.14618/) (2024)
- [Automatic Root Cause Analysis via Large Language Models for Cloud Incidents](https://mlsanity.com/paper/2305.15778/) (2023)
- [Exploring LLM-based Agents for Root Cause Analysis](https://mlsanity.com/paper/2403.04123/) (2024)
- [Explainable AI: current status and future directions](https://mlsanity.com/paper/2107.07045/) (2021)
- [Towards Optimizing the Costs of LLM Usage](https://mlsanity.com/paper/2402.01742/) (2024)
- [xFraud: Explainable Fraud Transaction Detection](https://mlsanity.com/paper/2011.12193/) (2020)
- [Semi-supervised Credit Card Fraud Detection via Attribute-Driven Graph Representation](https://mlsanity.com/paper/2412.18287/) (2024)
- [Elephants Never Forget: Testing Language Models for Memorization of Tabular Data](https://mlsanity.com/paper/2403.06644/) (2024)
- [ChatIDS: Advancing Explainable Cybersecurity Using Generative AI](https://mlsanity.com/paper/2306.14504/) (2023)
- [Cyber Sentinel: Exploring Conversational Agents in Streamlining Security Tasks with GPT-4](https://mlsanity.com/paper/2309.16422/) (2023)

## Built on by (most cited first, 2 of 2)

- [What LLMs explain is not what they believe: Evaluating explanation sufficiency under models' own input beliefs](https://mlsanity.com/paper/2606.28615/) (2026)
- [Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows](https://mlsanity.com/paper/2607.13078/) (2026)

## Abstract (arXiv)

Credit card fraud mitigation plays a significant role in modern society. While fraud detection systems are essential, they often struggle to keep pace with the constantly evolving fraud techniques. As a result, fraud investigation is an important complementary process required for continuously improving detection models, identifying emerging fraud patterns, providing case explanations of to stakeholders, and maintaining customers' trust. However, fraud analysts are overwhelmed with an enormous number of alerts generated by credit card transaction monitoring systems. Each alert investigation requires careful attention, domain expertise, and thorough documentation of the investigation outcomes, leading to alert fatigue. To address this challenge, we introduce the first Fraud Investigation Assistant (FIA) framework, which employs multimodal large language models (LLMs) to automate key steps of credit card fraud investigation and generate explanatory reports. FIA leverages the reasoning, code execution, and vision capabilities of LLMs to collect relevant and logically consistent evidence while maintaining relatively short investigation trajectories. Experiments with the Sparkov and CCTD datasets show that FIA gradually improves the F1 score while investigating borderline cases, reaching 8% improvement after only 1,500 additional investigations. These results suggest that LLM-based agents can assist with automating substantial parts of the fraud investigation process and may be particularly useful for resolving ambiguous alerts.