# FinGuard: Detecting Financial Regulatory Non-Compliance in LLM Interactions Source: [FinGuard: Detecting Financial Regulatory Non-Compliance in LLM Interactions]() Collection index: [llms.txt]() Data updated: 2026-05-30T05:00:04.259Z Authors: Huaixia Dou, Jie Zhu, Minghao Wu, Shuo Jiang, Junhui Li, Lifan Guo, Feng Chen, Chi Zhang Published: 2026-05-28T06:20:45.000Z ## Abstract As large language models (LLMs) are increasingly deployed in financial services, a single non-compliant interaction can expose institutions to regulatory penalties and direct consumer harm. Existing guard models are built around general harm taxonomies and overlook violations grounded in specific financial regulations. We address this gap with a regulation-driven pipeline that operates directly on regulatory documents, inducing a financial compliance risk taxonomy and synthesizing grounded training data without any predefined violation categories. Instantiating the pipeline on Chinese financial regulations, we release \\textbf{FinGuard-Bench}, to our knowledge the first benchmark for financial regulatory compliance detection, with expert-annotated labels at both the query and response levels. We further train \\textbf{FinGuard}, a financial compliance detection model built on Qwen3-8B and trained on the regulation-grounded data via supervised fine-tuning and self-play reinforcement learning. On FinGuard-Bench, FinGuard substantially outperforms all baselines, including dedicated guard models and much larger general-purpose LLMs such as Qwen3.5-397B-A17B and GPT-5.1. Furthermore, FinGuard also preserves general safety capabilities and adapts to unseen institution-specific policies using policy documents alone. We will publicly release the code, prompts, and resources used in this work on GitHub. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Financial Compliance Classification on FinGuard-Bench query-level](): Financial Compliance Classification; FinGuard-Bench query-level; F1 Score: 90.23. - [Financial Compliance Classification on FinGuard-Bench response-level](): Financial Compliance Classification; FinGuard-Bench response-level; F1 Score: 85.43. - [Response Safety Classification on General-Domain Safety Benchmarks](): Response-level safety classification; General-domain safety benchmarks Response-Level; F1 Score: 82.37. - [Query-level Safety Classification on General-domain Safety Benchmarks](): Query-level safety classification; General-domain safety benchmarks Query-Level; F1 Score: 81. ## Original sources and implementation [Original paper]() [PDF]()