EU-Agent-Bench：衡量LLM智能体在欧盟法律下的违法行为
EU-Agent-Bench: Measuring Illegal Behavior of LLM Agents Under EU Law
AI总结：
提出EU-Agent-Bench基准，通过函数调用与法律引用评分标准对比，评估LLM智能体在欧盟法律下的合规性，并研究系统提示中法律摘录对合规的影响。
摘要：
大型语言模型（LLMs）正越来越多地通过提供可用工具在各种情境中作为智能体部署。然而，LLM智能体可能表现出不可预测的行为，包括采取不良和/或不安全的行动。为了衡量LLM智能体在欧盟立法背景下采取非法行动的潜在倾向，我们引入了EU-Agent-Bench，一个可验证的人工策划基准，用于评估智能体在良性用户输入可能导致非法行动的情况下与欧盟法律规范的符合程度。我们的基准涵盖多个类别的场景，包括数据保护、偏见/歧视和科学诚信，每个用户请求都允许对请求的行动进行合规和不合规的执行。通过将模型的函数调用与由相关立法引用详尽支持的评分标准进行比较，我们评估了前沿LLM的法律合规性，并进一步调查了在智能体系统提示中提供相关立法摘录以及明确合规指令对合规效果的影响。我们为研究社区发布了一个公开预览集，同时保留了一个私有测试集，以防止在评估即将推出的模型时出现数据污染。我们鼓励未来的工作将智能体安全基准扩展到不同的法律管辖区以及多轮和多语言交互。我们在\href{https://github.com/ilijalichkovski/eu-agent-bench}{此URL}上发布了我们的代码。
英文摘要：
Large language models (LLMs) are increasingly deployed as agents in various contexts by providing tools at their disposal. However, LLM agents can exhibit unpredictable behaviors, including taking undesirable and/or unsafe actions. In order to measure the latent propensity of LLM agents for taking illegal actions under an EU legislative context, we introduce EU-Agent-Bench, a verifiable human-curated benchmark that evaluates an agent's alignment with EU legal norms in situations where benign user inputs could lead to unlawful actions. Our benchmark spans scenarios across several categories, including data protection, bias/discrimination, and scientific integrity, with each user request allowing for both compliant and non-compliant execution of the requested actions. Comparing the model's function calls against a rubric exhaustively supported by citations of the relevant legislature, we evaluate the legal compliance of frontier LLMs, and furthermore investigate the compliance effect of providing the relevant legislative excerpts in the agent's system prompt along with explicit instructions to comply. We release a public preview set for the research community, while holding out a private test set to prevent data contamination in evaluating upcoming models. We encourage future work extending agentic safety benchmarks to different legal jurisdictions and to multi-turn and multilingual interactions. We release our code on \href{https://github.com/ilijalichkovski/eu-agent-bench}{this URL}.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
