FinGuard: Detecting Financial Regulatory Non-Compliance in LLM Interactions

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Dou, Huaixia, Zhu, Jie, Wu, Minghao, Jiang, Shuo, Li, Junhui, Guo, Lifan, Chen, Feng, Zhang, Chi
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917543028981760
author Dou, Huaixia
Zhu, Jie
Wu, Minghao
Jiang, Shuo
Li, Junhui
Guo, Lifan
Chen, Feng
Zhang, Chi
author_facet Dou, Huaixia
Zhu, Jie
Wu, Minghao
Jiang, Shuo
Li, Junhui
Guo, Lifan
Chen, Feng
Zhang, Chi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_29427
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle FinGuard: Detecting Financial Regulatory Non-Compliance in LLM Interactions
Dou, Huaixia
Zhu, Jie
Wu, Minghao
Jiang, Shuo
Li, Junhui
Guo, Lifan
Chen, Feng
Zhang, Chi
Computation and Language
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.
title FinGuard: Detecting Financial Regulatory Non-Compliance in LLM Interactions
topic Computation and Language
url https://arxiv.org/abs/2605.29427