Fin_Agent 在 FinEval 2026:多语言金融 NLP 的任务感知方法
原标题:Fin_Agent at FinEval 2026: Task-Aware Methods for Multilingual Financial NLP
AI 摘要
该论文介绍了 Fin_Agent 系统参加 FinEval 2026 多语言金融语言理解共享任务,涵盖希腊语金融命名实体识别、日语隐含沟通识别和多语言金融问答三个子任务。系统分别采用规则与零样本 Qwen2.5-32B 分类结合、可解释线索序数评分器、以及 BGE-M3 检索加 Qwen3-32B 生成的方法,并报告了各子任务的 F1 或准确率。作者指出方法存在数据集特定规则、手工线索和监督有限等局限,并公开了实现代码。
正文节选
Fin_Agent at FinEval 2026: Task-Aware Methods for Multilingual Financial NLP Abstract We present Fin_Agent, our submission to the FinEval 2026 shared task on multilingual financial language understanding. Our systems address Greek financial named-entity recognition, Japanese implicit communication recognition, and multilingual financial question answering. For Greek NER, we combine annotation-aware numeric rules with zero-shot Qwen2.5-32B classification, achieving 0.9521 public F1 and 0.8884 pri