研究人员开发了两个新系统 FinGuard 和 FinHarness，以增强大型语言模型（LLM）在金融服务中的安全性和监管合规性。FinGuard 基于 Qwen3-8B 构建，采用新颖的管道，直接从金融法规中提取合规规则，以检测不合规的交互。FinHarness 作为金融LLM代理的内联安全防护架，监控查询和工具调用，以防止未经授权的操作并减少昂贵的后期审计需求。这两个系统旨在降低LLM在敏感金融领域部署相关的风险。 AI
影响 这些系统旨在降低高风险金融行业中LLM的风险并提高其可靠性，有可能加速其采用。
排序理由 两篇研究论文介绍了用于金融领域LLM安全性和监管合规性的新颖系统。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2605.29427v1 Announce Type: new 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 gen…
arXiv:2605.27333v1 Announce Type: new Abstract: Finance LLM agents must simultaneously block prompt-induced unauthorized actions and approve legitimate multi-step business workflows. However, boundary filters often miss irreversible mid-trajectory tool calls, while post-hoc LLM j…
Finance LLM agents must simultaneously block prompt-induced unauthorized actions and approve legitimate multi-step business workflows. However, boundary filters often miss irreversible mid-trajectory tool calls, while post-hoc LLM judges perform auditing only after termination --…