datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
VISION_LANGUAGEA key question for understanding multimodal vs. language capabilities of models is what is
the relative strength of the spatial reasoning and understanding in each modality, as spatial understanding is
expected to be a strength for multimodality? To test this we created a procedurally generatable, synthetic dataset
to testing spatial reasoning, navigation, and counting. These datasets are challenging and by
being procedurally generated new versions can easily be created to combat the effects… See the full description on the dataset page: https://huggingface.co/datasets/microsoft/VISION_LANGUAGE.Spatial-Blind-Spots-in-Vision-Language-Modelslicense: mit
model_evaluated:
name: Qwen3-VL-2B-Instruct
url: https://huggingface.co/Qwen/Qwen3-VL-2B-Instruct
evaluation_notebook:
https://www.kaggle.com/code/wajidhassanmoosa/blind-spot-qwen3-2b
evaluation_setup: |
The model evaluated in this study is Qwen3-VL-2B-Instruct.
Evaluation was conducted using the Hugging Face Transformers library
with automatic device mapping (device_map="auto") and "bfloat16" dtype selection.
For each example:
The image was provided as part of a… See the full description on the dataset page: https://huggingface.co/datasets/hassan-wajid/Spatial-Blind-Spots-in-Vision-Language-Models.visionlanguagemodelogLanguage-Vision-Hallucinations
Dataset for Techen Project 095280
A comprehensive dataset for the Techen Project, focused on examining hallucinations in multi-modal AI-generated text by investigating model uncertainty, text generation patterns, and linguistic factors.
Columns Overview
image_link: URL to the image associated with each data row.
temperature: Temperature setting for text generation, controlling output randomness.
description: Text generated by the model for each image, using the… See the full description on the dataset page: https://huggingface.co/datasets/wrom/Language-Vision-Hallucinations.vision_language_pairs_data
Vision-Language Pairs Dataset
This dataset contains metadata about image-text pairs from various popular vision-language datasets.
Contents
vision_language_data/all_vision_language_images.csv: Combined metadata for all images (75629 records)
vision_language_data/all_vision_language_captions.csv: Combined captions for all images (86676 records)
dataset_statistics.csv: Summary statistics for each dataset
category_distribution.csv: Distribution of image categories across… See the full description on the dataset page: https://huggingface.co/datasets/Omarrran/vision_language_pairs_data.