结合对比洞察的RAG用于金融风险信息识别
Identifying Financial Risk Information Using RAG with a Contrastive Insight
- Department of Computer Science University of Illinois Chicago（伊利诺伊大学芝加哥分校计算机科学系）
- Surlamer Investments（Surlamer投资公司）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对RAG在金融专业推理中输出风险信息偏泛化的问题，提出在RAG上加入同行感知对比推理层，经人工股票研究内容验证，该方法在ROUGE、BERTScore指标上优于基线RAG。
AI中文摘要：
在专业领域中，人类通常会将新问题与相似案例进行对比，凸显细微差异并得出结论，而非孤立地分析信息。将大语言模型（LLM）的推理能力应用于专业场景并基于检索增强生成（RAG）框架时，该流程虽能捕捉上下文相关信息，却并未被设计用于检索可比案例或相关问题。\n 尽管RAG在提取事实性信息方面表现出色，但它在专业推理任务中的输出往往偏泛化，反映的是宽泛事实而非特定上下文的洞察。在金融领域，这会导致生成的风险信息适用于绝大多数企业，缺乏针对性。为解决这一局限，我们在RAG之上提出了一种具备同行感知的对比推理层。\n 与人工生成的股票研究及风险分析内容相比，我们的对比方法在ROUGE、BERTScore等文本生成指标上优于基线RAG模型。
英文摘要：
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.
