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

11 to 20 of 54 Results
tokenizer.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 - 30,7 MB - MD5: b3dec1f2064f0a6d92c152fc95aa1e14
Results and model outputs from the paper: MLLM-as-a-Judge for Financial Document Image Machine Translation
Results and model outputs from the paper: MLLM-as-a-Judge for Financial Document Image Machine Translation
Jun 9, 2026
Torterolo Orta, Yanco Amor, 2026, "Results and model outputs from the paper: MLLM-as-a-Judge for Financial Document Image Machine Translation", https://doi.org/10.21950/VBG0HP, e-cienciaDatos, V1
This dataset contains 4 CSV files, one for each model used in the experiments of the paper titled: MLLM-as-a-Judge for Financial Document Image Machine Translation. The paper explores an end-to-end (E2E) Document Image Machine Translation (DIMT) approach using Gemma 4 on financial reports from IBEX 35 companies. Since traditional Machine Translatio...
gemma4_26b_feedback_ollama_llm_judge.csv
Jun 9, 2026 - Results and model outputs from the paper: MLLM-as-a-Judge for Financial Document Image Machine Translation
Valores separados por comas - 6,2 MB - MD5: 41d6e02a79c02a283220cb20dee36551
gemma4_26b_ollama_llm_judge.csv
Jun 9, 2026 - Results and model outputs from the paper: MLLM-as-a-Judge for Financial Document Image Machine Translation
Valores separados por comas - 7,5 MB - MD5: dafe2779545a746728758aa42dad4df0
gemma4_4b_1e-5_llm_judge.csv
Jun 9, 2026 - Results and model outputs from the paper: MLLM-as-a-Judge for Financial Document Image Machine Translation
Valores separados por comas - 3,8 MB - MD5: 8829703b929f424a309b1a530e628c30
gemma4_4b_ollama_llm_judge.csv
Jun 9, 2026 - Results and model outputs from the paper: MLLM-as-a-Judge for Financial Document Image Machine Translation
Valores separados por comas - 4,8 MB - MD5: e021b72687a28b68ecf419565ced4a07
readme_en.txt
Jun 9, 2026 - Results and model outputs from the paper: MLLM-as-a-Judge for Financial Document Image Machine Translation
Texto plano - 6,7 KB - MD5: 2d704a4f57096c1b4acd8af55981eae1
DocumentaciónDocumentation
Descriptive document in English
readme_es.txt
Jun 9, 2026 - Results and model outputs from the paper: MLLM-as-a-Judge for Financial Document Image Machine Translation
Texto plano - 7,5 KB - MD5: 507ec749d003699b38e9361fd957ffc1
DocumentaciónDocumentation
Documento de ayuda en español
Bidirectional ES-EN financial translation model: translategemma-12b LoRA adapters using parallel annual reports from IBEX 35 companies
Bidirectional ES-EN financial translation model: translategemma-12b LoRA adapters using parallel annual reports from IBEX 35 companies
Jun 9, 2026
Torterolo Orta, Yanco Amor, 2026, "Bidirectional ES-EN financial translation model: translategemma-12b LoRA adapters using parallel annual reports from IBEX 35 companies", https://doi.org/10.21950/NKX2YN, e-cienciaDatos, V1
This is a fine-tuned model for bidirectional ES-EN financial translation. This repository contains the low-rank adapters (LoRA) resulting from fine-tuning the google/translategemma-12b-it model with a parallel dataset of financial reports from IBEX 35 companies. This model was specifically fine-tuned to be more adaptable to different input sizes (u...
adapter_config.json
Jun 9, 2026 - Bidirectional ES-EN financial translation model: translategemma-12b LoRA adapters using parallel annual reports from IBEX 35 companies
JSON - 1,1 KB - MD5: 19ea6cbd37d65dbe4bbd612881dcdf9d
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.