
Visual Language Models for Document Analysis
The Finnish Financial Supervisory Authority has developed visual language models to analyse complex regulatory documents, such as those related to sustainable finance disclosures. Unlike traditional NLP methods that rely on text extraction — often losing critical visual elements like charts and tables — this tool treats entire document pages as images, preserving both textual and visual context.
- Use cases, geography and tags
- Organizations that created, adopted or are mentioned
- Ecosystem position
- Link to the original asset
- Comments and reactions