# Operational Evidence Gaps for LLMs in Fraud Detection and Trust-and-Safety Workflows

arXiv: https://arxiv.org/abs/2607.13078 · HTML: https://mlsanity.com/paper/2607.13078/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 42 of its 69 references that are in the map.
- First posted on arXiv 12 Jul 2026.

## Builds on (most cited first, 30 of 42)

- [A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly](https://mlsanity.com/paper/2312.02003/) (2023)
- [Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents](https://mlsanity.com/paper/2410.02644/) (2024)
- [PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models](https://mlsanity.com/paper/2402.07867/) (2024)
- [AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts](https://mlsanity.com/paper/2404.05993/) (2024)
- [The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies](https://mlsanity.com/paper/2407.19354/) (2024)
- [Safeguarding Large Language Models: A Survey](https://mlsanity.com/paper/2406.02622/) (2024)
- [Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety](https://mlsanity.com/paper/2502.05206/) (2025)
- [Safety in Large Reasoning Models: A Survey](https://mlsanity.com/paper/2504.17704/) (2025)
- [LLMs for Explainable AI: A Comprehensive Survey](https://mlsanity.com/paper/2504.00125/) (2025)
- [Policy-as-Prompt: Rethinking Content Moderation in the Age of Large Language Models](https://mlsanity.com/paper/2502.18695/) (2025)
- [Content Moderation by LLM: From Accuracy to Legitimacy](https://mlsanity.com/paper/2409.03219/) (2024)
- [SLM-Mod: Small Language Models Surpass LLMs at Content Moderation](https://mlsanity.com/paper/2410.13155/) (2024)
- [From Judgment to Interference: Early Stopping LLM Harmful Outputs via Streaming Content Monitoring](https://mlsanity.com/paper/2506.09996/) (2025)
- [Learning Conformal Abstention Policies for Adaptive Risk Management in Large Language and Vision-Language Models](https://mlsanity.com/paper/2502.06884/) (2025)
- [How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition](https://mlsanity.com/paper/2603.15714/) (2026)
- [Poly-Guard: Massive Multi-Domain Safety Policy-Grounded Guardrail Dataset](https://mlsanity.com/paper/2506.19054/) (2025)
- [DGP: A Dual-Granularity Prompting Framework for Fraud Detection with Graph-Enhanced LLMs](https://mlsanity.com/paper/2507.21653/) (2025)
- [Can LLMs Find Fraudsters? Multi-level LLM Enhanced Graph Fraud Detection](https://mlsanity.com/paper/2507.11997/) (2025)
- [Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM](https://mlsanity.com/paper/2508.05775/) (2025)
- [AI Agents May Always Fall for Prompt Injections](https://mlsanity.com/paper/2605.17634/) (2026)
- [FlexGuard: Continuous Risk Scoring for Strictness-Adaptive LLM Content Moderation](https://mlsanity.com/paper/2602.23636/) (2026)
- [EXPLICATE: Enhancing Phishing Detection through Explainable AI and LLM-Powered Interpretability](https://mlsanity.com/paper/2503.20796/) (2025)
- [Breaking the Chain: A Causal Analysis of LLM Faithfulness to Intermediate Structures](https://mlsanity.com/paper/2603.16475/) (2026)
- [Co-Investigator AI: The Rise of Agentic AI for Smarter, Trustworthy AML Compliance Narratives](https://mlsanity.com/paper/2509.08380/) (2025)
- [Understanding Structured Financial Data with LLMs: A Case Study on Fraud Detection](https://mlsanity.com/paper/2512.13040/) (2025)
- [LLM Performance Predictors: Learning When to Escalate in Hybrid Human-AI Moderation Systems](https://mlsanity.com/paper/2601.07006/) (2026)
- [Dialect vs Demographics: Quantifying LLM Bias from Implicit Linguistic Signals vs. Explicit User Profiles](https://mlsanity.com/paper/2604.21152/) (2026)
- [UCCI: Calibrated Uncertainty for Cost-Optimal LLM Cascade Routing](https://mlsanity.com/paper/2605.18796/) (2026)
- [Exploring the In-Context Learning Capabilities of LLMs for Money Laundering Detection in Financial Graphs](https://mlsanity.com/paper/2507.14785/) (2025)
- [LLM-Enhanced Self-Evolving Reinforcement Learning for Multi-Step E-Commerce Payment Fraud Risk Detection](https://mlsanity.com/paper/2509.18719/) (2025)

## Abstract (arXiv)

LLMs are now proposed for fraud detection, scam investigation, content moderation, and other trust-and-safety workflows. Much of the public literature still evaluates them as models, with less attention to their behavior as components in operational pipelines. This creates a practical evidence question: what would justify placing an LLM inside a live workflow with latency, cost, escalation, human-review, and adversarial-risk constraints? We address this question through a fraud-first survey of deployment evidence. We code 49 operationally relevant sources on LLM use in fraud detection, investigation support, content moderation, and cross-cutting robustness (18 fraud, 14 moderation, 17 cross-cutting), supplemented by 15 contextual references that establish the survey boundaries. These sources include systems, benchmarks, frameworks, and deployment-relevant surveys, not 49 production deployments. The main finding is an evidence imbalance. Fraud supplies the largest task-specific portion of the coded corpus. The moderation papers, however, include more explicit public evidence on latency, cost, governance, and fairness. Among the 18 fraud and investigation sources, none report clean per-decision latency, per-decision dollar cost, or calibration evidence; most report offline task performance, retrieval gains, or case-study accuracy instead. The survey contributes a role-and-evidence organizing frame, FORTE, for locating LLMs as classifiers, retrieval interfaces, explanation generators, reviewer assistants, agents, feature extractors, or escalation components. It also contributes a minimum deployment-evidence checklist covering latency budget, cost per decision, decision threshold, explanation integrity, and adversarial pressure. The resulting agenda identifies studies needed to support deployment claims for LLM-based fraud and trust-and-safety work.