# Understanding Structured Financial Data with LLMs: A Case Study on Fraud Detection

arXiv: https://arxiv.org/abs/2512.13040 · HTML: https://mlsanity.com/paper/2512.13040/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 45 references that are in the map.
- First posted on arXiv 15 Dec 2025.

## Builds on (most cited first, 24 of 24)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [BloombergGPT: A Large Language Model for Finance](https://mlsanity.com/paper/2303.17564/) (2023)
- [In-Context Retrieval-Augmented Language Models](https://mlsanity.com/paper/2302.00083/) (2023)
- [Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters](https://mlsanity.com/paper/2008.08692/) (2020)
- [FinBERT: A Pretrained Language Model for Financial Communications](https://mlsanity.com/paper/2006.08097/) (2020)
- [TabM: Advancing Tabular Deep Learning with Parameter-Efficient Ensembling](https://mlsanity.com/paper/2410.24210/) (2024)
- [Large Language Models as Analogical Reasoners](https://mlsanity.com/paper/2310.01714/) (2023)
- [FinGPT: Instruction Tuning Benchmark for Open-Source Large Language Models in Financial Datasets](https://mlsanity.com/paper/2310.04793/) (2023)
- [BioRAG: A RAG-LLM Framework for Biological Question Reasoning](https://mlsanity.com/paper/2408.01107/) (2024)
- [Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducements](https://mlsanity.com/paper/2502.12904/) (2025)
- [FinMME: Benchmark Dataset for Financial Multi-Modal Reasoning Evaluation](https://mlsanity.com/paper/2505.24714/) (2025)
- [Large Language Models as Financial Data Annotators: A Study on Effectiveness and Efficiency](https://mlsanity.com/paper/2403.18152/) (2024)
- [SEFraud: Graph-based Self-Explainable Fraud Detection via Interpretative Mask Learning](https://mlsanity.com/paper/2406.11389/) (2024)
- [Can LLMs Find Fraudsters? Multi-level LLM Enhanced Graph Fraud Detection](https://mlsanity.com/paper/2507.11997/) (2025)
- [FCMR: Robust Evaluation of Financial Cross-Modal Multi-Hop Reasoning](https://mlsanity.com/paper/2412.12567/) (2024)
- [Advanced Real-Time Fraud Detection Using RAG-Based LLMs](https://mlsanity.com/paper/2501.15290/) (2025)
- [DiMA: An LLM-Powered Ride-Hailing Assistant at DiDi](https://mlsanity.com/paper/2503.04768/) (2025)

## Built on by (most cited first, 4 of 4)

- [Understanding LLM Evaluator Behavior: A Structured Multi-Evaluator Framework for Merchant Risk Assessment](https://mlsanity.com/paper/2602.05110/) (2026)
- [Bypassing Document Ingestion: An MCP Approach to Financial Q&A](https://mlsanity.com/paper/2603.20316/) (2026)
- [Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows](https://mlsanity.com/paper/2607.13078/) (2026)
- [SR-Fraud: An Outcome-Supervised Reflective LLM Agent Framework for Non-Stationary Payment Fraud Detection](https://mlsanity.com/paper/2609.27287/) (2026)

## Abstract (arXiv)

Detecting fraud in financial transactions typically relies on tabular models that demand heavy feature engineering to handle high-dimensional data and offer limited interpretability, making it difficult for humans to understand predictions. Large Language Models (LLMs), in contrast, can produce human-readable explanations and facilitate feature analysis, potentially reducing the manual workload of fraud analysts and informing system refinements. However, they perform poorly when applied directly to tabular fraud detection due to the difficulty of reasoning over many features, the extreme class imbalance, and the absence of contextual information. To bridge this gap, we introduce FinFRE-RAG, a two-stage approach that applies importance-guided feature reduction to serialize a compact subset of numeric/categorical attributes into natural language and performs retrieval-augmented in-context learning over label-aware, instance-level exemplars. Across four public fraud datasets and three families of open-weight LLMs, FinFRE-RAG substantially improves F1/MCC over direct prompting and is competitive with strong tabular baselines in several settings. Although these LLMs still lag behind specialized classifiers, they narrow the performance gap and provide interpretable rationales, highlighting their value as assistive tools in fraud analysis.