# Recognition Is Not Grounding: Benchmarking Multilingual Financial Evidence Extraction

arXiv: https://arxiv.org/abs/2610.19432 · HTML: https://mlsanity.com/paper/2610.19432/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 26 references that are in the map.
- First posted on arXiv 14 Oct 2026.

## Builds on (most cited first, 15 of 15)

- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [FinQA: A Dataset of Numerical Reasoning over Financial Data](https://mlsanity.com/paper/2109.00122/) (2021)
- [TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance](https://mlsanity.com/paper/2105.07624/) (2021)
- [XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation](https://mlsanity.com/paper/2104.07412/) (2021)
- [MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual Data](https://mlsanity.com/paper/2206.01347/) (2022)
- [DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression](https://mlsanity.com/paper/2609.19969/) (2026)
- [DocFinQA: A Long-Context Financial Reasoning Dataset](https://mlsanity.com/paper/2401.06915/) (2024)
- [FiNER: Financial Numeric Entity Recognition for XBRL Tagging](https://mlsanity.com/paper/2203.06482/) (2022)
- [Fino1: On the Transferability of Reasoning-Enhanced LLMs and Reinforcement Learning to Finance](https://mlsanity.com/paper/2502.08127/) (2025)
- [Plutus: Benchmarking Large Language Models in Low-Resource Greek Finance](https://mlsanity.com/paper/2502.18772/) (2025)
- [Krikri: Advancing Open Large Language Models for Greek](https://mlsanity.com/paper/2505.13772/) (2025)
- [Financial Numeric Extreme Labelling: A Dataset and Benchmarking for XBRL Tagging](https://mlsanity.com/paper/2306.03723/) (2023)
- [Hierarchical Retrieval with Evidence Curation for Open-Domain Financial Question Answering on Standardized Documents](https://mlsanity.com/paper/2505.20368/) (2025)
- [Parameter-Efficient Instruction Tuning of Large Language Models For Extreme Financial Numeral Labelling](https://mlsanity.com/paper/2405.06671/) (2024)
- [Unlocking Data Value in Finance: A Study on Distillation and Difficulty-Aware Training](https://mlsanity.com/paper/2603.07223/) (2026)

## Abstract (arXiv)

Comparing financial disclosures across languages requires identifying shared accounting concepts and recovering all numerical facts that express them. Existing benchmarks evaluate aspects of these capabilities, but provide limited insight into whether both succeed on the same multilingual evidence. In particular, it remains unclear whether language models can recognize these concepts across languages and exhaustively recover their corresponding numerical evidence from the same contexts. We introduce MULTIFINGROUND, a benchmark designed to investigate this recognition-grounding gap in multilingual financial reports. Constructed from FY2025 disclosures of 90 issuers in English, French, and Greek, MULTIFINGROUND aligns independently authored reports through a shared accounting taxonomy and provides traceable fact-level annotations. The benchmark evaluates financial fact identification, concept recognition, exhaustive fact selection, and concept discrimination without candidate labels. Across 15 evaluated models, eight API and open-weight reference models achieve 97.3-99.4% concept recognition accuracy, yet miss at least one target fact in 26.6-41.9% of correctly recognized groups. Further analyses reveal substantial variation in concept discrimination and limited gains from the evaluated finance-specialized models. Our findings demonstrate that strong concept recognition can coexist with incomplete evidence recovery, highlighting the importance of evaluating semantic recognition and evidence completeness together.