# SAFE-QAQ: End-to-End Slow-Thinking Audio-Text Fraud Detection via Reinforcement Learning

arXiv: https://arxiv.org/abs/2601.01392 · HTML: https://mlsanity.com/paper/2601.01392/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 25 references that are in the map.
- First posted on arXiv 4 Jan 2026.

## Builds on (most cited first, 14 of 14)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning](https://mlsanity.com/paper/2209.14610/) (2022)
- [ReFT: Reasoning with Reinforced Fine-Tuning](https://mlsanity.com/paper/2401.08967/) (2024)
- [GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot](https://mlsanity.com/paper/2412.02612/) (2024)
- [Monte Carlo Tree Search: A Review of Recent Modifications and Applications](https://mlsanity.com/paper/2103.04931/) (2021)
- [Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction](https://mlsanity.com/paper/2502.11946/) (2025)
- [Solving Math Word Problems via Cooperative Reasoning induced Language Models](https://mlsanity.com/paper/2210.16257/) (2022)
- [Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search](https://mlsanity.com/paper/2502.02508/) (2025)
- [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)
- [Interactive Continual Learning: Fast and Slow Thinking](https://mlsanity.com/paper/2403.02628/) (2024)
- [TeleAntiFraud-28k: An Audio-Text Slow-Thinking Dataset for Telecom Fraud Detection](https://mlsanity.com/paper/2503.24115/) (2025)
- [Advanced Real-Time Fraud Detection Using RAG-Based LLMs](https://mlsanity.com/paper/2501.15290/) (2025)
- [DetoxBench: Benchmarking Large Language Models for Multitask Fraud & Abuse Detection](https://mlsanity.com/paper/2409.06072/) (2024)
- [Exposing LLM Vulnerabilities: Adversarial Scam Detection and Performance](https://mlsanity.com/paper/2412.00621/) (2024)

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

- [ORACLE: Anticipating Scams from Partial Trajectories in Streaming App Usage](https://mlsanity.com/paper/2605.16363/) (2026)
- [ThinkDeception: A Progressive Reinforcement Learning Framework for Interpretable Multimodal Deception Detection](https://mlsanity.com/paper/2606.18988/) (2026)

## Abstract (arXiv)

Existing fraud detection methods predominantly rely on transcribed text, suffering from ASR errors and missing crucial acoustic cues like vocal tone and environmental context. This limits their effectiveness against complex deceptive strategies. To address these challenges, we first propose SAFE-QAQ, an end-to-end comprehensive framework for audio-based slow-thinking fraud detection. First, the SAFE-QAQ framework eliminates the impact of transcription errors on detection performance. Secondly, we propose rule-based slow-thinking reward mechanisms that systematically guide the system to identify fraud-indicative patterns by accurately capturing fine-grained audio details, through hierarchical reasoning processes. Besides, our framework introduces a dynamic risk assessment framework during live calls, enabling early detection and prevention of fraud. Experiments on the TeleAntiFraud-Bench demonstrate that SAFE-QAQ achieves dramatic improvements over existing methods in multiple key dimensions, including accuracy, inference efficiency, and real-time processing capabilities. Currently deployed and analyzing over 70,000 calls daily, SAFE-QAQ effectively automates complex fraud detection, reducing human workload and financial losses. Code: https://anonymous.4open.science/r/SAFE-QAQ.