mlsanityData to 14 Oct 2026

IGT @ FinMMEval 2026 Task 2: Question-Type Prompting with Targeted Extraction for Multilingual Financial QA

arXiv 2609.08139 ↗First posted 8 Sep 2026cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 9 of its 13 references that are in the map. First posted on arXiv 8 Sep 2026.

Builds on

9 of 13 references.

References · 9

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  3. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 517
  4. 2019Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answeringcited by 147
  5. 2024Improving Retrieval for RAG based Question Answering Models on Financial Documentscited by 49
  6. 2025FinRAGBench-V: A Benchmark for Multimodal RAG with Visual Citation in the Financial Domaincited by 16
  7. 2025MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Applicationcited by 14
  8. 2024Multi-Reranker: Maximizing performance of retrieval-augmented generation in the FinanceRAG challengecited by 10
  9. 2024Systematic Evaluation of Long-Context LLMs on Financial Conceptscited by 6

Built on by

Not cited yet.