# DetoxBench: Benchmarking Large Language Models for Multitask Fraud & Abuse Detection

arXiv: https://arxiv.org/abs/2409.06072 · HTML: https://mlsanity.com/paper/2409.06072/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 33 references that are in the map.
- First posted on arXiv 9 Sep 2024.

## Builds on (most cited first, 16 of 16)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems](https://mlsanity.com/paper/1905.00537/) (2019)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [CTRL: A Conditional Transformer Language Model for Controllable Generation](https://mlsanity.com/paper/1909.05858/) (2019)
- [ToxicChat: Unveiling Hidden Challenges of Toxicity Detection in Real-World User-AI Conversation](https://mlsanity.com/paper/2310.17389/) (2023)
- [Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good](https://mlsanity.com/paper/1906.06725/) (2019)
- [How Context Affects Language Models' Factual Predictions](https://mlsanity.com/paper/2005.04611/) (2020)

## Built on by (most cited first, 5 of 5)

- [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)
- [Gen-AI for User Safety: A Survey](https://mlsanity.com/paper/2411.06606/) (2024)
- [SAFE-QAQ: End-to-End Slow-Thinking Audio-Text Fraud Detection via Reinforcement Learning](https://mlsanity.com/paper/2601.01392/) (2026)
- [The System Prompt Is the Attack Surface: How LLM Agent Configuration Shapes Security and Creates Exploitable Vulnerabilities](https://mlsanity.com/paper/2603.25056/) (2026)
- [Harm in AI-Driven Societies: An Audit of Toxicity Adoption on Chirper.ai](https://mlsanity.com/paper/2601.01090/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have demonstrated remarkable capabilities in natural language processing tasks. However, their practical application in high-stake domains, such as fraud and abuse detection, remains an area that requires further exploration. The existing applications often narrowly focus on specific tasks like toxicity or hate speech detection. In this paper, we present a comprehensive benchmark suite designed to assess the performance of LLMs in identifying and mitigating fraudulent and abusive language across various real-world scenarios. Our benchmark encompasses a diverse set of tasks, including detecting spam emails, hate speech, misogynistic language, and more. We evaluated several state-of-the-art LLMs, including models from Anthropic, Mistral AI, and the AI21 family, to provide a comprehensive assessment of their capabilities in this critical domain. The results indicate that while LLMs exhibit proficient baseline performance in individual fraud and abuse detection tasks, their performance varies considerably across tasks, particularly struggling with tasks that demand nuanced pragmatic reasoning, such as identifying diverse forms of misogynistic language. These findings have important implications for the responsible development and deployment of LLMs in high-risk applications. Our benchmark suite can serve as a tool for researchers and practitioners to systematically evaluate LLMs for multi-task fraud detection and drive the creation of more robust, trustworthy, and ethically-aligned systems for fraud and abuse detection.