IGT system improves multilingual financial question answering with smart prompt techniques
IGT @ FinMMEval 2026 Task 2: Question-Type Prompting with Targeted Extraction for Multilingual Financial QA
Computation and LanguageArtificial Intelligence
Summary
The paper focuses on improving question answering systems that handle financial documents in multiple languages. The authors found that different types of questions need different methods: simple numeric questions work best with keyword searches, while more complex questions require rules to pick the right information from news articles. Their approach led to a large improvement over a standard baseline system and performed well in an international competition. This shows that tailoring methods to question types can help computers better answer financial questions in several languages.
financial question answeringmultilingual NLPkeyword extractionrule-based systemsROUGE evaluationSEC filingsnews article analysisprompt engineeringinformation retrieval
Authors
Yuwen Chiu
Abstract
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.