datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
FinQA-hallucination-detection
FinQA Hallucination Detection
Dataset Summary
This dataset was created from a subset of the original FinQA dataset. For each user query (financial questions), we prompted an LLM to generate a response to this query based on provided context (financial statements and tables from the original FinQA).
Each generated LLM response is labeled based on whether it is correct or not. This dataset is thus useful for benchmarking reference-free LLM Eval and Hallucination… See the full description on the dataset page: https://huggingface.co/datasets/Cleanlab/FinQA-hallucination-detection.whisper-hallucinations
Whisper Hallucinations on Noise
Dataset Summary
This dataset lists common hallucinations from OpenAI Whisper when the input has no speech.
We build it from a noise-only corpus.
We run Whisper on noise clips.
We collect any non-empty text that Whisper outputs.
We deduplicate phrases and count how often they occur.
Use it to test, detect, and reduce non-speech hallucinations.
Motivation
ASR models often output text on silence or noise.
These false hits harm UX… See the full description on the dataset page: https://huggingface.co/datasets/sachaarbonel/whisper-hallucinations.Phantom_Hallucination_Detection
Phantom: A Benchmark for Hallucination Detection in Financial Long-Context QA
Authors: Lanlan Ji, Dominic Seyler, Gunkirat Kaur, Manjunath Hegde, Koustuv Dasgupta, Bing Xiang
This is the repository containing the dataset for the submission mentioned above.
This dataset is designed for hallucination detection in language models. It includes multiple variants of the Phantom dataset with different token lengths (seed, 2k, 5K, 10K, 20K, 30K) for long context experiments , segments… See the full description on the dataset page: https://huggingface.co/datasets/seyled/Phantom_Hallucination_Detection.legal_rag_hallucinations
Dataset Card for Hallucination Free? Assessing the Reliability of Leading AI Legal Research Tools
This data release contains the queries and raw model outputs we analyze in Magesh, Surani, Dahl, Suzgun, Manning and Ho, Hallucination Free? Assessing the Reliability of Leading AI Legal Research Tools, Journal of Empirical Legal Studies (2024, forthcoming).
Consistent with emerging understanding of AI
benchmarking and leaderboards, we reserve a random sample of 50% of the dataset to… See the full description on the dataset page: https://huggingface.co/datasets/reglab/legal_rag_hallucinations.FinQA-hallucination-detection
FinQA Hallucination Detection
Dataset Summary
This dataset was created from a subset of the original FinQA dataset. For each user query (financial questions), we prompted an LLM to generate a response to this query based on provided context (financial statements and tables from the original FinQA).
Each generated LLM response is labeled based on whether it is correct or not. This dataset is thus useful for benchmarking reference-free LLM Eval and Hallucination… See the full description on the dataset page: https://huggingface.co/datasets/kankshith123/FinQA-hallucination-detection.LLM-Hallucination-Detection-complex-mathematics
AIME Hallucination Detection Dataset
This dataset is created for detecting hallucinations in Large Language Models (LLMs), particularly focusing on complex mathematical problems. It can be used for tasks like model evaluation, fine-tuning, and research.
Dataset Details
Name: AIME Hallucination Detection Dataset
Format: CSV
Size: (add size, e.g., 10MB)
Files Included:
AIME-hallucination-detection-dataset.csv: Contains the dataset.
Content Description… See the full description on the dataset page: https://huggingface.co/datasets/tourist800/LLM-Hallucination-Detection-complex-mathematics.Taming-Hallucinations
Taming Hallucinations: Boosting MLLMs' Video Understanding via Counterfactual Video Generation
CVPR 2026 Findings
Project Page | Paper | Code
Dataset Summary
This repository hosts DualityVidQA, the large-scale paired video–QA dataset introduced in
Taming Hallucinations: Boosting MLLMs' Video Understanding via Counterfactual Video Generation.
Taming Hallucinations introduces DualityForge, a controllable diffusion-based framework that turns
real videos into… See the full description on the dataset page: https://huggingface.co/datasets/GD-ML/Taming-Hallucinations.rag-hallucination-benchmark
RAG Hallucination Benchmark
Context
Retrieval-Augmented Generation (RAG) is the industry standard for reducing LLM hallucinations, but detecting when a RAG system fails is a massive challenge. Most existing benchmarks focus only on massive Deep Learning models and lack tabular features.
This dataset provides a clean, engineered setup to train models (from XGBoost to RoBERTa) to detect hallucinations, predict context faithfulness, and measure answer relevance.… See the full description on the dataset page: https://huggingface.co/datasets/vkshdev/rag-hallucination-benchmark.Phantom_Hallucination_Detection
Phantom: A Benchmark for Hallucination Detection in Financial Long-Context QA
Authors: Lanlan Ji, Dominic Seyler, Gunkirat Kaur, Manjunath Hegde, Koustuv Dasgupta, Bing Xiang
This is the repository containing the dataset for the submission mentioned above.
This dataset is designed for hallucination detection in language models. It includes multiple variants of the Phantom dataset with different token lengths (seed, 2k, 5K, 10K, 20K, 30K) for long context experiments , segments… See the full description on the dataset page: https://huggingface.co/datasets/Anindita1979/Phantom_Hallucination_Detection.AIME_Hallucination_Detection
AIME Hallucination Detection Dataset
This dataset is created for detecting hallucinations in Large Language Models (LLMs), particularly focusing on complex mathematical problems. It can be used for tasks like model evaluation, fine-tuning, and research.
Dataset Details
Name: AIME Hallucination Detection Dataset
Format: CSV
Size: (14.6 MB)
Files Included:
AIME-hallucination-detection-dataset.csv: Contains the dataset.
Content Description
The dataset… See the full description on the dataset page: https://huggingface.co/datasets/tourist800/AIME_Hallucination_Detection.Language-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.python_wiki_hallucination_graded
RAG + Instruction Following Results from Python Wikipedia benchmark
This dataset is an artifact from an experiment conducted by Arthur
Experiment
We wanted to compare how good LLMs are at answering questions using a context. Doing this task well involves an inverse skill: recognizing when the necessary information to answer a question is absent, and choosing instead to not answer. One name for this is “staying grounded” in the context that you provide in your prompt to… See the full description on the dataset page: https://huggingface.co/datasets/Arthur-AI/python_wiki_hallucination_graded.hallucination-traps
Hallucination Traps
A curated benchmark dataset consisting of intentionally misleading prompts designed to evaluate hallucination behavior in language models.
Each prompt appears plausible at first glance but contains a subtle false premise, nonexistent entity, or incorrect factual assumption. The expected behavior is that the model should either refuse, express uncertainty, or explicitly identify the incorrect premise rather than hallucinate a confident but false answer.… See the full description on the dataset page: https://huggingface.co/datasets/benchmark-data/hallucination-traps.neural-bridge-rag-hallucination
RAG Hallucination Dataset Overview
This dataset can be used to test hallucinations in Retrieval-Augmented Generation (RAG) systems.It is based on: neural-bridge/rag-hallucination-dataset-1000
Data Instances
Each data point includes a context, a question about the context, and an answer.
A typical example looks like this:
{
"context": "...",
"question": "...",
"answer": "..."
}
Data Fields
context: Context to provide to the LLM.
question: A question… See the full description on the dataset page: https://huggingface.co/datasets/SridharKumarKannam/neural-bridge-rag-hallucination.ai-5node-infer-buf-lag-cpl-hallucination-propagation-v0.1
What this repo does
This dataset models hallucination propagation in agent ecosystems. It detects when inference pressure, weakened verification buffer, governance lag in review, and tight coupling through shared knowledge and automation cross the five-node cascade threshold into an unrecoverable hallucination propagation cascade.
This dataset models a five-node cascade: four interacting instability drivers and one emergent cascade state.The fifth node represents the nonlinear… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/ai-5node-infer-buf-lag-cpl-hallucination-propagation-v0.1.hallucination_dolly_benchmarkhallucination_wikibiohallucination_evaluationXL_SUM_ukr_synthetic_hallucinationsDataset contains 1239 articles out of the validation set from https://huggingface.co/datasets/csebuetnlp/xlsum/blob/main/xlsum.py.
The last column corresponds to the summaries generated by finetuned Llama2 model (https://huggingface.co/SGaleshchuk/Llama-2-13b-hf_uk_rank-32_ft). Generqted summaries have been also corrupted with GPT-4.
Here is an algorithm applied: we extract named entities from the generated summaries using the Spacy NER model for
Ukrainian and pass the first occurred entity… See the full description on the dataset page: https://huggingface.co/datasets/SGaleshchuk/XL_SUM_ukr_synthetic_hallucinations.llm_hallucinationsJourneyBench_Hallucinationhallucination_testHallucination_Evaluationhallucination-sft-v0Generalized_Hallucination_Risk_Level_100k_Prompts
Generalized Hallucination Risk Level — 100k Prompts
A dataset of ~108,000 prompts labeled for hallucination risk (LOW / MEDIUM / HIGH)
generated to train pre-inference classifiers for Large Language Models.
Dataset Description
Prompts were synthetically generated to cover a wide range of topics and difficulty
levels, then labeled via a multi-model consensus protocol. Three independent LLMs
evaluated each prompt; agreement determined the final risk label.
Columns… See the full description on the dataset page: https://huggingface.co/datasets/hb0810/Generalized_Hallucination_Risk_Level_100k_Prompts.algozee_rag-based-hallucination-reduction-in-llms
RAG-Based Hallucination Reduction in LLMs
Introduction to Large Language Models and Hallucination Problem
Dataset Info
Source: Kaggle
Original Size: 0.17 MB
Kaggle Downloads: 43
Files: 1
Files
llm_rag_dataset_6k.csv.csv
Mirrored from Kaggle
Vietnamese_Hallucinationsmollm2-microbiology-hallucinations
SmolLM2 Blind Spot Audit — Microbiology & Nepal Community Health Triage
Overview
This dataset contains 10 manually audited prompt-output pairs from HuggingFaceTB/SmolLM2-1.7B
(base model, not instruct), testing its performance on two domain-specific categories:
Microbiology laboratory protocols — Gram staining, serial dilution, PCR parameters,
selective media interpretation
Community health triage in Nepal — FCHV danger sign protocols, MUAC malnutrition
thresholds… See the full description on the dataset page: https://huggingface.co/datasets/Suman989/smollm2-microbiology-hallucinations.