DetoxBench: Benchmarking Large Language Models for Multitask Fraud & Abuse Detection
This work addresses the need for systematic evaluation of LLMs in high-stake fraud and abuse detection applications, though it is incremental as it extends existing benchmarking approaches to a new domain.
The authors introduced DetoxBench, a comprehensive benchmark suite to evaluate large language models (LLMs) on multitask fraud and abuse detection across scenarios like spam emails and hate speech, finding that while LLMs show proficient baseline performance, they struggle with tasks requiring nuanced pragmatic reasoning such as identifying misogynistic language.
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.