FinLLM-KG：知识图谱增强LLM的金融情感分析
原标题：FinLLM-KG: Knowledge Graph-Enhanced LLMs for Financial Sentiment Analysis in Algorithmic Trading
AI 摘要
该论文提出 FinLLM-KG，一个模型无关的框架，将因果 LLM 与金融知识图谱结合，在推理时注入来自 SEC 10-K 文件的公司级知识，无需更新模型权重。上下文以自然语言公司简介或少量相关性排序的事实三元组形式提供，使情感预测能考虑公司层面的信息，并可将预测归因到具体句子和知识图谱事实以增强可解释性。模拟实验表明，该框架在投资组合表现上持续优于现有基线。
正文节选
FinLLM-KG: Knowledge Graph-Enhanced LLMs for Financial Sentiment Analysis in Algorithmic Trading Abstract Recent advances in Generative AI have substantially improved financial sentiment analysis through post-trained financial large language models (LLMs). However, existing approaches remain confined to predicting the sentiment of each article in isolation and operate as black boxes, which limits contextual understanding and hinders deployment in high-stakes financial decision-making. To this en