datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
factuality-rmbench-style
Factuality RM-Bench Style
Factuality RM-Bench Style is a controlled English dataset for studying whether
reward models and representation probes prefer stylistic presentation over
factual correctness. Each row contains one question, a localized correct and
incorrect proposition, and six responses formed by crossing correctness with
three presentation styles: concise, normal, and Markdown.
This repository is an export package for
factuality_rmbench_style_v6. The published data… See the full description on the dataset page: https://huggingface.co/datasets/Yunnnuy/factuality-rmbench-style.Factuality_Alignment
Factual Preference Alignment Dataset
**⚠️ Warning:**This dataset contains hallucinated and synthetic responses
intentionally generated for research on robust factuality alignment.
Responses may include fabricated or incorrect information by design
to support the evaluation of hallucination-aware learning.
Dataset Summary
The AIXpert Preference Alignment Dataset is a curated collection of
45,000 factuality-aware preference pairs designed to support
research on Modified… See the full description on the dataset page: https://huggingface.co/datasets/vector-institute/Factuality_Alignment.factuality-benchmark-preview
AIgentic Factuality Benchmark — Preview
This repository is a placeholder for AIgentic’s upcoming open benchmark for evaluating factuality and hallucination control in enterprise AI systems.
🧭 Purpose
Our goal is to set a new reliability standard for AI models deployed in high-stakes professional domains — such as law, finance, and consulting.
🔬 Coming Soon
Example benchmark dataset (legal factuality)
Architecture overview diagram
LLM-as-a-Judge evaluation… See the full description on the dataset page: https://huggingface.co/datasets/AIgenticLLC/factuality-benchmark-preview.factuality-v0