Overview of FinMMEval 2026 Task 2: Multilingual Financial Short-Answer Question Answering

2026-07-22

AI Summary

This work addresses the challenge of generating concise and accurate answers to English questions based on multilingual financial documents—including English, Chinese, Japanese, Spanish, and Greek—by introducing the first cross-lingual short-answer question answering benchmark in the financial domain. The task requires systems to produce succinct responses grounded in multilingual financial reports and news articles, evaluated using ROUGE-1 F1. The benchmark features difficulty-stratified question templates, a standardized submission format, and incorporates advanced techniques such as retrieval-augmented generation, cross-lingual evidence processing, structured prompting, and answer compression with validation. Twelve systems participated, with the top four achieving performance within less than one percentage point of each other, reflecting both intense competition and the effectiveness of current methodologies.

Abstract

FinMMEval 2026 Task 2 evaluates short-answer financial question answering over multilingual evidence. Each final-test item pairs an English question with financial statements and news in English, Chinese, Japanese, Spanish, and Greek. Participating systems submit one concise answer per item in JSONL format. The final-test set contains 256 items, split evenly between easy and expert tiers; each tier contains four question templates instantiated over 32 company-report groups. Gold answers were withheld during submission, and systems were ranked by macro-averaged item-level ROUGE-1 F1 against organizer-held reference answers. The final leaderboard includes 12 ranked submissions. The strongest systems are closely clustered, with the top four separated by less than one percentage point in ROUGE-1 F1. The submitted system papers document retrieval-augmented generation, cross-lingual evidence handling, structured prompting, answer compression, and validation strategies.

Problem

• multilingual
• financial question answering
• short-answer
• cross-lingual

Innovation

• multilingual financial QA
• retrieval-augmented generation
• cross-lingual evidence handling
• structured prompting
• answer compression