About GRESEL: AI Generation Results Enriched with Simplified Explanations Based on Linguistic Features.

GRESEL: AI Generation Results Enriched with Simplified Explanations Based on Linguistic Features, is a coordinated research project funded by the Spanish Ministry of Science, Innovation and Universities. This initiative addresses the critical need to enhance the transparency and trustworthiness of responses generated by increasingly prevalent generative Artificial Intelligence (AI) applications. Recognizing the potential of these technologies across various domains, GRESEL focuses on enriching their output with simplified, linguistically grounded explanations.

The project is structured into two distinct, yet interconnected subprojects, each exploring specific facets of this overarching goal. This one is GRESEL-UAM: Financial Narratives and Literature.

It is led by Dr. Antonio Moreno-Sandoval. GRESEL-UAM delves into the intersection of financial narratives and literature. This subproject investigates how generative AI can be employed to analyze and understand complex financial texts and literary works. Furthermore, it aims to develop methods for generating AI responses in these domains that are not only accurate but also accompanied by clear and accessible explanations rooted in linguistic features present in the original texts. By focusing on these specific areas, GRESEL-UAM seeks to contribute to more nuanced and interpretable AI applications in both the financial and literary fields.

Featured Dataverses

In order to use this feature you must have at least one published or linked dataverse.

Publish Dataverse

Are you sure you want to publish your dataverse? Once you do so it must remain published.

Publish Dataverse

This dataverse cannot be published because the dataverse it is in has not been published.

Delete Dataverse

Are you sure you want to delete your dataverse? You cannot undelete this dataverse.

Advanced Search

1 to 10 of 54 Results
EN-ES financial multimodal translation model (DIMT): gemma-4-E4B LoRA adapters (EN image -> ES text) fine-tuned on annual reports from IBEX 35 companies
EN-ES financial multimodal translation model (DIMT): gemma-4-E4B LoRA adapters (EN image -> ES text) fine-tuned on annual reports from IBEX 35 companies
Jun 9, 2026
Torterolo Orta, Yanco Amor; Stanescu, Maria Alexia, 2026, "EN-ES financial multimodal translation model (DIMT): gemma-4-E4B LoRA adapters (EN image -> ES text) fine-tuned on annual reports from IBEX 35 companies", https://doi.org/10.21950/HEZRAQ, e-cienciaDatos, V1
This is a fine-tuned model for EN-ES financial multimodal translation, that is, translating directly from the English page image to the written Spanish text. This kind of multimodal translation is known as Document Image Machine Translation (DIMT). More specifically, this repository contains the low-rank adapters (LoRA) resulting from fine-tuning t...
adapter_config.json
Jun 9, 2026 - EN-ES financial multimodal translation model (DIMT): gemma-4-E4B LoRA adapters (EN image -> ES text) fine-tuned on annual reports from IBEX 35 companies
JSON - 1,6 KB - MD5: 71327d0681b503ba28f59bf0b17a78e1
adapter_model.safetensors
Jun 9, 2026 - EN-ES financial multimodal translation model (DIMT): gemma-4-E4B LoRA adapters (EN image -> ES text) fine-tuned on annual reports from IBEX 35 companies
Desconocido - 314,6 MB - MD5: 8b2e0aafe7f9cd0b2dc71cb6a88c85e4
chat_template.jinja
Jun 9, 2026 - EN-ES financial multimodal translation model (DIMT): gemma-4-E4B LoRA adapters (EN image -> ES text) fine-tuned on annual reports from IBEX 35 companies
Desconocido - 1,5 KB - MD5: 686d5278bab1d04b816c17dc2625f713
full_logs.csv
Jun 9, 2026 - EN-ES financial multimodal translation model (DIMT): gemma-4-E4B LoRA adapters (EN image -> ES text) fine-tuned on annual reports from IBEX 35 companies
Valores separados por comas - 626 B - MD5: b8aa6d14cbad7309c9feff0c236d2b34
processor_config.json
Jun 9, 2026 - EN-ES financial multimodal translation model (DIMT): gemma-4-E4B LoRA adapters (EN image -> ES text) fine-tuned on annual reports from IBEX 35 companies
JSON - 1,7 KB - MD5: 745faf3efeeb530f121ac97ab3fc5ad7
readme_en.txt
Jun 9, 2026 - EN-ES financial multimodal translation model (DIMT): gemma-4-E4B LoRA adapters (EN image -> ES text) fine-tuned on annual reports from IBEX 35 companies
Texto plano - 5,7 KB - MD5: f06af08e5aaa873d48f8d1e7f746aba9
DocumentaciónDocumentation
Descriptive document in English
readme_es.txt
Jun 9, 2026 - EN-ES financial multimodal translation model (DIMT): gemma-4-E4B LoRA adapters (EN image -> ES text) fine-tuned on annual reports from IBEX 35 companies
Texto plano - 6,5 KB - MD5: b4ade06a880304992a1a1b7e644744b3
Documentation
Documento de ayuda en español
README.md
Jun 9, 2026 - EN-ES financial multimodal translation model (DIMT): gemma-4-E4B LoRA adapters (EN image -> ES text) fine-tuned on annual reports from IBEX 35 companies
Marcado de texto - 1,5 KB - MD5: fb9d004ec8b5151a76667fff503b614d
DocumentaciónDocumentation
tokenizer_config.json
Jun 9, 2026 - EN-ES financial multimodal translation model (DIMT): gemma-4-E4B LoRA adapters (EN image -> ES text) fine-tuned on annual reports from IBEX 35 companies
JSON - 2,6 KB - MD5: b3b2f6c8ef1772d2980977ce1c63c6fb
Add Data

Log in to create a dataverse or add a dataset.

Log In
Share Dataverse

Share this dataverse on your favorite social media networks.

Link Dataverse
Reset Modifications

Are you sure you want to reset the selected metadata fields? If you do this, any customizations (hidden, required, optional) you have done will no longer appear.