Results show that DeepScrub improves fraud review accuracy, reduces first-stage review workload, and provides traceable evidence for production risk-review workflows, showing that domain adaptation can matter more than model scale in this setting.
Abstract
Detecting fake-order fraud at scale remains a critical challenge for large online-to-offline (O2O) service platforms, as existing approaches often rely on expert-designed features, produce black-box decisions, and provide limited interpretability. To address these limitations, we propose DeepScrub, a reinforcement learning framework built upon large language models (LLMs) for fake-order fraud detection with traceable reasoning. DeepScrub introduces three innovations. First, a semantic unification module converts heterogeneous risk signals into textual descriptions that LLMs can understand. Second, continued pre-training on risk-control corpora injects domain knowledge, and task rewards jointly evaluate prediction correctness and reasoning quality. Third, the SUggest-REflect (SURE) mechanism incorporates expert feedback and model self-checking to iteratively refine reasoning paths. On a real-world fake-order fraud detection dataset, DeepScrub achieves a macro-F1 score of 85.3%, outperforming the best baseline by 2.7 percentage points. Our task-optimized 8B model further surpasses a 32B model, showing that domain adaptation can matter more than model scale in this setting. In a four-week live pilot, DeepScrub achieved 91.8% precision and 88.5% recall, improving over first-stage human reviewers by 16.6 and 38.8 percentage points. It reduced first-stage manual review workload by 94% and saved nearly one million RMB annually. These results show that DeepScrub improves fraud review accuracy, reduces first-stage review workload, and provides traceable evidence for production risk-review workflows.
It is concluded that each component of a layered fraud system contributes only under specific conditions, and that a plausible rationale from an investigation agent is not evidence of a better decision.
A fraud-first survey of deployment evidence identifies studies needed to support deployment claims for LLM-based fraud and trust-and-safety work and finds an evidence imbalance.
Recent fake news detection pipelines increasingly leverage large language models and vision-language models for reasoning-based analysis. However, several challenges remain open: improving reasoning quality through self-reflection without ground-truth chain-of-thought supervision, using improved reasoning to benefit downstream model fine-tuning, and connecting single-sample fraudulent-pattern discovery with cross-sample verification. We propose SRM-FND, a self-reflective multimodal reasoning framework for short-video fake news detection. SRM-FND develops higher-quality reasoning through contrastive deliberation, iterative root-cause diagnosis, and corrective prompt refinement. A Blind Analyst, Counter-Conclusion Reasoner, and Self-Consistency Arbiter collaboratively identify and retain discriminative rationales. The framework also incorporates dual-phase, topic-adaptive vision-language model fine-tuning to improve multimodal grounding and enable lightweight topic specialization. For uncertain cases, it performs confidence-driven cross-sample review by retrieving credible and suspicious co-event examples. Experiments on FakeSV and FakeTT show that SRM-FND outperforms strong baselines, produces more reliable and interpretable predictions, and delivers noticeable improvements in cross-dataset performance.
Pin-Jie Xu, Yuzhou Yang, Zhisheng Tan et al.· 0 citations
It is shown that the quality of the generated risk indicators is the main driver of zero-shot cyber threat detection performance, and that retrieval mainly benefits weaker LLMs by generating more discriminative risk indicators, whereas stronger models achieve comparable performance without retrieved context.
A. Al-Ghamdi, S. Layeghy, Marius Portmann· 0 citations
This work constructs and makes publicly available a comprehensive U.S. company dataset combining financial statements, summarized MD&A text, and fraud labels and achieves the best performance on the challenging CI-FSFD task, demonstrating the critical value of textual data and robust evaluation for reliable financial fraud detection.
Guy Stephane Waffo Dzuyo, Gaël Guibon, Christophe Cerisara et al.· arXiv.org· 0 citations
Financial statement fraud inflicts large and recurring losses on capital markets, yet the dominant detection paradigm still relies on single, black-box classifiers (e.g., RUSBoost) trained on structured accounting ratios alone. Two limitations follow: (i) the rich, unstructured Management Discussion and Analysis (MD&A) narrative of the 10-K filing is discarded, and (ii) the resulting scores are difficult for auditors to trust because they carry no transparent, standards-aligned rationale. Recent large language model (LLM) systems have shown that multi-agent collaboration is more robust than a single LLM for anomaly detection, but no study has systematically transferred this paradigm to listed-company statement fraud. We propose FraudDebate-Agent, a four-role multi-agent system in which a Quantitative Analyst agent scores 28 raw accounting items and 14 ratios with gradient-boosted and tabular attention models, a Narrative Auditor agent quantifies tone, linguistic uncertainty, and year-over-year textual novelty of the MD&A with FinBERT, and an Industry Peer agent uses retrieval-augmented generation to measure industry-relative anomaly. A Critic–Debate agent then orchestrates a pair-wise Evidence-based Multi-Agent Debate (EMAD) that reconciles disagreement across modalities and arbitrates a reconciled fraud-risk assessment, which is aggregated over a tri-modal evidence graph. Our contributions are as follows: (1) the first use of an evidence-grounded debate mechanism for accounting fraud, which materially reduces LLM hallucination; (2) a numerical–textual–peer evidence graph that fuses heterogeneous signals; and (3) an explainable report aligned with the PCAOB AS 2401 fraud-risk taxonomy. On AAER-labelled firm-years linked across a SEC financial dataset and EDGAR-CORPUS, FraudDebate-Agent improves the area under the ROC curve and the rare-event ranking metric NDCG@k over the strongest single-modality and single-LLM baselines while producing substantially more faithful explanations. We frame the system as a fraud-risk screening and risk-ranking tool for AAER-labelled misstatement risk rather than a determination of fraudulent intent. We report results over multiple seeds to reflect real-world stochasticity and discuss limitations and cross-domain applications.
