用多智能体系统提升信贷评估，模仿真实决策流程
MASCA: LLM based-Multi Agents System for Credit Assessment
- 设计分层智能体协同处理信贷评估任务
- 对比学习优化风险与收益判断，准确率超基线模型
- 揭示多智能体结构的理论机制，适合金融风控研究者
近年来，金融问题求解开始融合大语言模型（LLM）与基于智能体的系统，主要集中在交易和金融建模领域。然而，信贷评估仍是一个研究不足的挑战，传统上依赖规则和统计模型。本文提出MASCA，一种基于大语言模型的多智能体系统，旨在通过模拟现实决策过程来提升信贷评估能力。该框架采用分层架构，由专门的LLM智能体协作完成子任务，并引入对比学习进行风险与回报评估以优化决策。我们还从信号博弈论视角分析了层级式多智能体系统的结构与交互，提供理论洞察。此外，论文包含对信贷评估中偏见的详细分析，关注公平性问题。实验表明，MASCA在性能上优于基线方法，验证了层级式LLM多智能体系统在金融应用中的有效性，尤其在信用评分方面表现突出。
原文摘要 · Abstract (English)
Recent advancements in financial problem-solving have leveraged LLMs and agent-based systems, with a primary focus on trading and financial modeling. However, credit assessment remains an underexplored challenge, traditionally dependent on rule-based methods and statistical models. In this paper, we introduce MASCA, an LLM-driven multi-agent system designed to enhance credit evaluation by mirroring real-world decision-making processes. The framework employs a layered architecture where specialized LLM-based agents collaboratively tackle sub-tasks. Additionally, we integrate contrastive learning for risk and reward assessment to optimize decision-making. We further present a signaling game theory perspective on hierarchical multi-agent systems, offering theoretical insights into their structure and interactions. Our paper also includes a detailed bias analysis in credit assessment, addressing fairness concerns. Experimental results demonstrate that MASCA outperforms baseline approaches, highlighting the effectiveness of hierarchical LLM-based multi-agent systems in financial applications, particularly in credit scoring.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。