用对比推理提升金融风险识别，让大模型更懂相似案例间的差异。
Identifying Financial Risk Information Using RAG with a Contrastive Insight
- 在RAG基础上增加对比推理层，主动寻找可比公司案例
- 相比基线RAG，生成内容在ROUGE和BERTScore上显著提升
- 适合需要深度对比分析的金融研究与风控场景
在专业领域中，人类常通过对比相似案例来发现细微差异并得出结论，而非孤立分析信息。当使用大语言模型结合RAG处理专业任务时，虽然能获取相关上下文，但缺乏检索可比案例或相关问题的能力。现有RAG在金融领域输出往往泛化，仅反映多数企业共有的通用风险。为此，我们提出一种基于对比推理的增强层，使RAG不仅能提取事实，还能识别相似案例并突出差异。实验表明，该方法在文本生成指标（如ROUGE、BERTScore）上优于基线RAG，且生成结果更接近人工撰写的投资研究报告与风险分析。
原文摘要 · Abstract (English)
In specialized domains, humans often compare new problems against similar examples, highlight nuances, and draw conclusions instead of analyzing information in isolation. When applying reasoning in specialized contexts with LLMs on top of a RAG, the pipeline can capture contextually relevant information, but it is not designed to retrieve comparable cases or related problems. While RAG is effective at extracting factual information, its outputs in specialized reasoning tasks often remain generic, reflecting broad facts rather than context-specific insights. In finance, it results in generic risks that are true for the majority of companies. To address this limitation, we propose a peer-aware comparative inference layer on top of RAG. Our contrastive approach outperforms baseline RAG in text generation metrics such as ROUGE and BERTScore in comparison with human-generated equity research and risk.
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。