OpenData-Benchmark-Ita

In a Nutshell

Project:

Villanova

Company:

Villanova.ai

Repository URL:

https://huggingface.co/datasets/VillanovaAI/OpenData-Benchmark-ITA

Open Source License:

ODC-BY-1.0

About the Repository

Functionality

Dataset-OpenData-Benchmark-ITA is a multiple-choice benchmark dataset designed to evaluate the capability of Large Language Models (LLMs) to understand, retrieve, and reason over public Open Data published by European government portals. The current release focuses exclusively on Italian Open Data and is based on datasets published on the official Italian government portal, data.gov.it. Future releases will extend the benchmark to include harmonized governmental Open Data from additional European countries, starting with France, Spain, and Germany.

IPCEI-CIS Referene Architecture

AI Layer, Data Layer

Keywords

applied-nlp-benchmark, benchmark-dataset, csv-metadata-pairs, curated-dataset, data-gov-it, data-metadata-understanding, dataset-understanding, document-grounding, european-open-data, evaluation-suite, government-open-data, italian-benchmark-dataset, italian-language-dataset, italian-nlp, italian-open-data, knowledge-benchmark, llm-evaluation, llm-testing, metadata-reasoning, multiple-choice-qa, odc-by-license, open-data-benchmark, public-sector-ai, question-answering-dataset, real-world-data-benchmark, reasoning-benchmark, retrieval-based-qa, structured-qa, supervised-benchmark, tabular-data-qa, villanova-ai