基于指令微调小型语言模型的渐进式老年金融诈骗增量风险评估

中文摘要 AI 辅助

针对老年人的金融诈骗日益通过电子邮件、短信、电话等文本和语音渠道发生，这些诈骗会经历多轮对话：从伪装或偶然接触开始，通过建立信任和制造紧迫感逐步升级，最终以索要敏感信息或要求转账为结束。由于风险信号会在多轮对话中逐步出现，有效的检测需要模型在资源受限的部署场景下持续更新风险评估。我们提出了一种基于累计轮次的风险评估框架，该框架可逐步聚合对话轮次并在每一步重新评估风险，从而实现对渐进式演变对话的动态诈骗监控。我们构建了一个多轮对话数据集，涵盖投资、慈善和技术支持诈骗场景，每个对话包含2至8轮，且在每一轮累计阶段都标注了定性风险等级、连续风险评分、解释性理由和安全建议。我们对四个小型语言模型（Phi-4、LLaMA-3.2、DeepSeek-R1和Qwen3）进行了微调，并在统一训练框架下进行评估。微调后的小型模型能够捕捉与诈骗相关的语言线索和跨轮升级模式，同时保持适合移动设备及资源受限部署的紧凑架构。在评估的模型中，Phi-4和LLaMA-3.2相对于其参数规模实现了更强的轮次感知风险评估性能。这些结果表明，结构化累计建模可支持面向部署场景的增量诈骗风险评估，同时凸显了紧凑语言模型在隐私感知和设备端诈骗保护方面的潜力。

英文摘要

Financial scams targeting older adults increasingly occur through text and voice channels such as email, SMS, and phone calls, unfolding over multiple conversational turns that begin with impersonation or casual contact, escalate through trust building and urgency, and culminate in requests for sensitive information or financial transfers. Because risk signals emerge incrementally across turns, effective detection requires models that continuously update risk estimates under resource-constrained deployment settings. We propose a cumulative turn-based risk assessment framework that incrementally aggregates conversational turns and re-estimates risk at each step, enabling dynamic scam monitoring across progressively evolving conversations. A multi-turn dialogue dataset is constructed to cover investment, charity, and tech support scam scenarios, with each dialogue containing two to eight turns and annotated at every cumulative stage with a qualitative risk level, a continuous risk score, an explanatory rationale, and a safety recommendation. Four small language models (Phi-4, LLaMA-3.2, DeepSeek-R1, and Qwen3) are fine-tuned and evaluated under a unified training framework. Fine-tuned small models capture fraud-related linguistic cues and cross-turn escalation patterns while maintaining compact architectures suitable for mobile and resource-constrained deployment settings. Among the evaluated models, Phi-4 and LLaMA-3.2 achieve stronger turn-aware risk estimation performance relative to their parameter scale. These results suggest that structured cumulative modeling can support incremental scam risk assessment in deployment-oriented settings while highlighting the potential of compact language models for privacy-aware and on-device fraud protection.

发表机构

• Kansas State University（堪萨斯州立大学）

机构由 AI 辅助整理，请以论文原文为准。