datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
rag_hallucinationsProvides examples of hallucinated responses for RAG applications.
hallucination-autopsy-benchmark
Hallucination Autopsy Benchmark
A unified, standardized benchmark for cross-model, cross-parameter analysis of LLM hallucination phenomena.
Overview
This dataset merges multiple hallucination detection benchmarks into a single standardized schema, enabling systematic etiological analysis of why and how different LLM architectures hallucinate under specific configurations.
Version: 3.0.0Total Records: 69,002Base Records: 69,002Augmented Records: 0Hallucination… See the full description on the dataset page: https://huggingface.co/datasets/OiQ/hallucination-autopsy-benchmark.groundtruth-hallucination-bench-sample
Groundtruth Data Hallucination Benchmark Sample
This public teaser contains 180 representative, source-backed examples from Groundtruth Data products.
Groundtruth Data builds verified evaluation, remediation, and held-out validation datasets for AI models using authoritative source data. The commercial workflow is:
Find where a model fails.
Prove the failure with a larger verified evaluation.
Provide targeted remediation/training data.
Validate improvement on untouched held-out… See the full description on the dataset page: https://huggingface.co/datasets/Groundtruth-Data/groundtruth-hallucination-bench-sample.curatorkit-testrun-Hallucination
curatorkit-testrun-Hallucination
Built using CuratorKIT — provenance-grounded curation and synthesis for LLM post-training.
Method
qa
Backend
litellm
Model
openai/Qwen/Qwen2.5-0.5B-Instruct
Formats
alpaca
Artifact
dataset
Published
2026-08-28 10:47 UTC
Usage
from datasets import load_dataset
ds = load_dataset("ram-lexsi/curatorkit-testrun-Hallucination", "alpaca")
hallucination-reduction-dpo-100k
Hallucination Reduction DPO (100K)
100,000 DPO preference pairs training LLMs to stay within knowledge bounds. The chosen response is accurate and appropriately uncertain; the rejected response is confident but wrong — fabricated statistics, fake citations, wrong facts, overclaimed certainty.
Motivation
Hallucination is the #1 reliability concern blocking enterprise LLM adoption. Models fail in predictable patterns:
Inventing specific statistics with false… See the full description on the dataset page: https://huggingface.co/datasets/stindardlogic/hallucination-reduction-dpo-100k.basta_allucinazioni_ai_prompt-enough_hallucinations_ai_prompt
Basta allucinazioni / Enough hallucinations
A small multilingual prompt dataset for AI custom instructions. The goal is to encourage an AI system to admit uncertainty instead of inventing an answer.
Main prompt
Italian original
Se non conosci una risposta ad una domanda che ti è stata fatta non inventare, rispondi semplicemente: non lo so.
English reference
If you do not know the answer to a question you have been asked, do not make… See the full description on the dataset page: https://huggingface.co/datasets/pietrorisipr-2025/basta_allucinazioni_ai_prompt-enough_hallucinations_ai_prompt.hallucination-grounding-dpo-4k
Hallucination Grounding DPO Pairs (4K)
DPO preference pairs targeting the full spectrum of factuality failures — from hallucination to over-hedging.
Motivation
Existing refusal/safety datasets focus on what not to say. This dataset targets the orthogonal challenge: when to say "I don't know" vs. when to answer confidently. Models that over-refuse waste user trust; models that hallucinate destroy it.
Dataset Description
4,000 preference pairs across… See the full description on the dataset page: https://huggingface.co/datasets/stindardlogic/hallucination-grounding-dpo-4k.ko-hallucination-benchmark
Hallucination Benchmark v1
Dataset Description
Hallucination Benchmark는 한국어 LLM의 환각(Hallucination) 탐지 성능을 평가하기 위한 벤치마크 데이터셋입니다.
Dataset Summary
언어: 한국어 (Korean)
샘플 수: 244개
태스크: 6가지 (Coding, Dialogue, General, Math, QA, Summarization)
환각 타입: 5가지 (No Hallucination, Factual Contradiction, Factual Fabrication, Instruction Inconsistency, Logical Inconsistency)
Supported Tasks
이 벤치마크는 다음과 같은 태스크를 포함합니다:
Coding (40 samples): 코드 생성 및 프로그래밍 문제
Dialogue (40… See the full description on the dataset page: https://huggingface.co/datasets/jiwon9703/ko-hallucination-benchmark.RAGTruth-Hallucinations
ToolACE
ToolACE is an automatic agentic pipeline designed to generate Accurate, Complex, and divErse tool-learning data.
ToolACE leverages a novel self-evolution synthesis process to curate a comprehensive API pool of 26,507 diverse APIs.
Dialogs are further generated through the interplay among multiple agents, guided by a formalized thinking process.
To ensure data accuracy, we implement a dual-layer verification system combining rule-based and model-based checks.
More details… See the full description on the dataset page: https://huggingface.co/datasets/drond0174/RAGTruth-Hallucinations.