datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
frames-benchmark
FRAMES: Factuality, Retrieval, And reasoning MEasurement Set
FRAMES is a comprehensive evaluation dataset designed to test the capabilities of Retrieval-Augmented Generation (RAG) systems across factuality, retrieval accuracy, and reasoning.
Our paper with details and experiments is available on arXiv: https://arxiv.org/abs/2409.12941.
Dataset Overview
824 challenging multi-hop questions requiring information from 2-15 Wikipedia articles
Questions span diverse topics… See the full description on the dataset page: https://huggingface.co/datasets/google/frames-benchmark.OmniBrainBench
OmniBrainBench
🍎 Homepage|💻 GitHub|🤗 Dataset|📖 Paper
This repository is the official implementation of the paper [OmniBrainBench: A Comprehensive Multimodal Benchmark for Brain Imaging Analysis Across Multi-stage Clinical Tasks].
🚀 News
[02/2026] Our OmniBrainBench is accepted by CVPR2026!
[12/2025] We have released the evaluation code and dataset for OmniBrainBench.
[11/2025] The manuscript can be found on arXiv.
🚀Overview
we introduce… See the full description on the dataset page: https://huggingface.co/datasets/FrankPN/OmniBrainBench.ethical-framework-UNESCO-Ethics-of-AI
Ethical AI Training Dataset
Introduction
UNESCO's Ethics of Artificial Intelligence, adopted by 193 Member States in November 2021, represents the first global framework for ethical AI development and deployment.
While regional initiatives like The Montréal Declaration for a Responsible Development of Artificial Intelligence emphasize community-driven governance, UNESCO's approach establishes comprehensive international standards through coordinated multi-stakeholder… See the full description on the dataset page: https://huggingface.co/datasets/ktiyab/ethical-framework-UNESCO-Ethics-of-AI.ethical-framework
1. Dataset Title
Ethical AI Decision-Making Training Data (Montreal Declaration Edition)
2. Overview
This dataset contains carefully crafted scenarios (instructions) and detailed responses illustrating step-by-step ethical reasoning aligned with the principles outlined in the Montreal Declaration for Responsible AI. Each entry poses a complex ethical challenge and provides a reasoned solution while referencing the specific principle(s) being tested.
These entries can… See the full description on the dataset page: https://huggingface.co/datasets/ktiyab/ethical-framework.fracas
Dataset Card for FraCaS
Dataset Summary
This repository contains the French version of the FraCaS Test Suite introduced in this paper, as well as the original English one, in a TSV format (as opposed to the XML format provided with the original paper).
FraCaS stands for "Framework for Computational Semantics".
Supported Tasks and Leaderboards
This dataset can be used for the task of Natural Language Inference (NLI), also known as Recognizing Textual Entailment… See the full description on the dataset page: https://huggingface.co/datasets/maximoss/fracas.RRNCBPublic
RRNCB: Russian RAG Normative – Corporate Benchmark (Sample)
1. Доступ к данным и структура
В данном репозитории представлена общедоступная часть (sample) первого российского бенчмарка для оценки RAG-решений.
а) Ссылка на архив исходных документов: Файлы
б) Ссылка на текущий репозиторий HF: Hugging-Face репозиторий
в) Состав репозитория:
dataset_sample.csv — таблица с вопросами и ответами.
Архив — набор из 65 PDF-файлов, являющихся источниками знаний.
2.… See the full description on the dataset page: https://huggingface.co/datasets/FractalGPT/RRNCBPublic.RRNCBFinalPublic
RRNCB: Russian RAG Normative – Corporate Benchmark (Sample)
1. Доступ к данным и структура
В данном репозитории представлена часть для контрольной проверки, в рамках первого российского бенчмарка для оценки RAG-решений.
а) Ссылка на архив исходных документов: Файлы
б) Ссылка на текущий репозиторий HF: Hugging-Face репозиторий
в) Состав репозитория:
dataset_sample.csv — таблица с вопросами и ответами.
Архив — набор из 65 PDF-файлов, являющихся источниками знаний.… See the full description on the dataset page: https://huggingface.co/datasets/FractalGPT/RRNCBFinalPublic.FRACTURED-SORRY-Bench-Automated-Multishot-Jailbreak
FRACTURED-SORRY-Bench: Framework for Revealing Attacks in Conversational Turns Undermining Refusal Efficacy and Defenses over SORRY-Bench (Automated Multi-shot Jailbreaks)
Dataset Card for FRACTURED-SORRY-Bench Dataset
🌐Website
📑Paper
📚Dataset
💻Github
FRACTURED-SORRY-Bench is a framework for evaluating the safety of Large Language Models (LLMs) against multi-turn conversational attacks. Building upon the SORRY-Bench dataset, we propose a simple… See the full description on the dataset page: https://huggingface.co/datasets/AmanPriyanshu/FRACTURED-SORRY-Bench-Automated-Multishot-Jailbreak.frames-benchmark
FRAMES: Factuality, Retrieval, And reasoning MEasurement Set
FRAMES is a comprehensive evaluation dataset designed to test the capabilities of Retrieval-Augmented Generation (RAG) systems across factuality, retrieval accuracy, and reasoning.
Our paper with details and experiments is available on arXiv: https://arxiv.org/abs/2409.12941.
Dataset Overview
824 challenging multi-hop questions requiring information from 2-15 Wikipedia articles
Questions span diverse… See the full description on the dataset page: https://huggingface.co/datasets/cyan12343/frames-benchmark.