FinDialogLens：多方可对话事件抽取识别金融聊天室漏单
原标题：FinDialogLens: Event Extraction over Multi-Party Dialogue for Missed-Trade Identification in Financial Chatrooms
AI 摘要
该论文提出 FinDialogLens，将多方可对话金融聊天室中的漏单识别建模为事件抽取任务。系统采用混合 LLM 流水线：先用微调的 RoBERTa 分类器检测 RFQ 触发消息、价格与交易结果线索，再按事件切分 RFQ 窗口，最后由 GPT-4o 或微调开源 LLM 填充论元角色。在最终价格和交易结果上分别达到 92.1% 和 94.3% 准确率，优于全聊天室 CoT 提示；难度感知路由器将 85% 的 LLM 调用降级到规则引擎，在 7 万 RFQ/天规模下每天节省超 300 美元。
正文节选
FinDialogLens: Event Extraction over Multi-Party Dialogue for Missed-Trade Identification in Financial Chatrooms Abstract Multi-party financial chatrooms are vital for sales-and-trading professionals, but their complexity makes manual recovery of missed trades infeasible: each Request for Quote (RFQ) is an event whose final price and trade outcome appear many messages after the RFQ-trigger message (the inquiry message), interleaved with concurrent RFQs from other participants. We cast this as ev