面向人类的LLM-智能体系统用于检测异常数字资产交易
Human-Centered LLM-Agent System for Detecting Anomalous Digital Asset Transactions
AI总结：
HCLA是一种面向人类的多智能体系统，用于通过自然语言交互提高数字资产交易异常检测的可解释性和透明度。
摘要：
我们提出了HCLA，一种面向人类的多智能体系统，用于检测数字资产交易中的异常。该系统集成了三个认知对齐的角色：规则抽象、证据评分和专家式论证。这些角色在一个对话流程中运作，使非专家能够用自然语言表达分析意图，检查结构化的风险证据，并获得可追溯的、基于情境的推理。该系统采用开源的网页接口实现，将用户意图转换为显式的分析规则，应用经典异常检测器来量化证据风险，并重建基于可观察交易信号的专家式论证。在加密货币异常数据集上的实验表明，尽管底层检测器实现了强大的预测准确性，HCLA显著提高了可解释性、交互性和决策透明性。重要的是，HCLA不是为了在传统XAI意义上解释黑箱模型而设计的。相反，我们重建了一个可追溯的专家推理过程，使算法证据与监管和调查判断对齐。通过明确将证据评分与专家式论证分开，该框架强调责任，而不仅仅是可解释性，并满足监管、审计和以合规为导向的金融取证的实际需求。我们描述了系统架构、闭环交互设计、数据集、评估协议和限制。我们认为，一种人机协同的推理重建范式对于在高风险金融环境中实现透明度、责任和信任是至关重要的。关键词：面向人类的人工智能；LLM-智能体系统；多智能体架构；异常检测；数字资产交易；加密货币取证；区块链分析；人机协同；可解释人工智能（XAI）；可解释性
英文摘要：
We present HCLA, a human-centered multi-agent system for anomaly detection in digital-asset transactions. The system integrates three cognitively aligned roles: Rule Abstraction, Evidence Scoring, and Expert-Style Justification. These roles operate in a conversational workflow that enables non-experts to express analytical intent in natural language, inspect structured risk evidence, and obtain traceable, context-aware reasoning. Implemented with an open-source, web-based interface, HCLA translates user intent into explicit analytical rules, applies classical anomaly detectors to quantify evidential risk, and reconstructs expert-style justifications grounded in observable transactional signals. Experiments on a cryptocurrency anomaly dataset show that, while the underlying detector achieves strong predictive accuracy, HCLA substantially improves interpretability, interaction, and decision transparency. Importantly, HCLA is not designed to explain a black-box model in the conventional XAI sense. Instead, we reconstruct a traceable expert reasoning process that aligns algorithmic evidence with regulatory and investigative judgment. By explicitly separating evidence scoring from expert-style justification, the framework emphasizes accountability beyond explainability and addresses practical requirements for regulatory, audit, and compliance-driven financial forensics. We describe the system architecture, closed-loop interaction design, datasets, evaluation protocol, and limitations. We argue that a human-in-the-loop reasoning reconstruction paradigm is essential for achieving transparency, accountability, and trust in high-stakes financial environments. Keywords: Human-Centered AI; LLM-Agent System; Multi-Agent Architecture; Anomaly Detection; Digital Asset Transactions; Cryptocurrency Forensics; Blockchain Analytics; Human-in-the-Loop; Explainable AI (XAI); Interpretability
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。
