针对多语言金融问答，区分数值型与综合型问题，分别用关键词提取和新闻筛选策略提升准确率。
IGT @ FinMMEval 2026 Task 2: Question-Type Prompting with Targeted Extraction for Multilingual Financial QA
- 按问题类型分治：数值类直接抽关键词，综合类用规则筛选多语种新闻段落。
- 开发集ROUGE-1达0.395，较通用RAG基线提升60%，测试集排名第三。
- 适合关注多语言金融信息抽取、需精准答案生成的场景。
我们提出IGT系统参与CLEF 2026年FinMMEval实验室的PolyFiQA任务2，该任务基于英文财报文件及多语言新闻（英、中、日、西、希）对四家公司进行多语言金融问答。分析发现，44个开发集问题可分为两类：结构化数值类（如研发占比、现金流、资本支出）宜通过财报文本中的关键词直接提取；合成类（如投资策略、资本分配、前三大收入来源）则需基于规则的多语言新闻段落选择。数据集分析显示，每类合成问题的19个参考答案中，有17-18个共享相同证据标签前缀，其单字词元直接贡献于ROUGE-1重合度。最终系统在开发集上达到约0.395的ROUGE-1，相较通用RAG基线（约0.247）提升60%相对性能；在官方测试集上位列第3，得分为ROUGE-1 = 0.3071，Precision = 0.2821，Recall = 0.4044。
原文摘要 · Abstract (English)
We present the IGT system for PolyFiQA Task 2 of the FinMMEval Lab at CLEF 2026, a multilingual financial question answering task over English SEC filings and multilingual news articles (English, Chinese, Japanese, Spanish, Greek) for four companies. Our central observation is that the 344 development questions divide into two families requiring fundamentally different approaches: structured numeric types (R&D ratio, cash flow, capital expenditure) are best answered by direct keyword extraction on filing text, while synthesis types (investment strategy, capital allocation, top-three revenue focuses) require rule-based multilingual news passage selection. A dataset analysis reveals that 17-18 of 19 ground-truth reference answers per synthesis type share an exact evidence label prefix, whose unigram tokens contribute directly to ROUGE-1 overlap. The final system achieves development ROUGE-1 approximately 0.395, a 60% relative improvement over a generic RAG baseline (approximately 0.247), and ranks 3rd of 12 teams on the official test set with ROUGE-1 = 0.3071, Precision = 0.2821, and Recall = 0.4044.
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。