用对比学习将银行客户行为序列压缩为短提示，提升效率与精度。
LATTE: Learning Aligned Transactions and Textual Embeddings for Bank Clients
- 用短提示压缩客户历史行为，降低计算开销。
- 在真实金融数据集上优于现有方法，推理速度更快。
- 适合对延迟敏感的实时风控与客户画像场景。
从客户的历史通信序列中学习嵌入表示是金融应用的核心。尽管大语言模型（LLMs）具备通用世界知识，但直接处理长序列事件在计算上成本高昂，难以部署于实际系统。本文提出LATTE，一种对比学习框架，将原始事件嵌入与冻结的LLM生成的语义嵌入对齐。行为特征被归纳为简短提示，经由LLM嵌入后作为对比损失的监督信号。该方法显著降低了推理成本与输入规模，相比传统全序列输入LLM的方式更具可行性。实验表明，该方法在真实金融数据集上优于当前最优事件序列表征技术，同时满足低延迟环境下的可部署要求。
原文摘要 · Abstract (English)
Learning clients embeddings from sequences of their historic communications is central to financial applications. While large language models (LLMs) offer general world knowledge, their direct use on long event sequences is computationally expensive and impractical in real-world pipelines. In this paper, we propose LATTE, a contrastive learning framework that aligns raw event embeddings with semantic embeddings from frozen LLMs. Behavioral features are summarized into short prompts, embedded by the LLM, and used as supervision via contrastive loss. The proposed approach significantly reduces inference cost and input size compared to conventional processing of complete sequence by LLM. We experimentally show that our method outperforms state-of-the-art techniques for learning event sequence representations on real-world financial datasets while remaining deployable in latency-sensitive environments.
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。