datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
RAGDOLL
The RAGDOLL E-Commerce Webpage Dataset
This repository contains the RAGDOLL (Retrieval-Augmented Generation Deceived Ordering via AdversariaL materiaLs) dataset as well as its LLM-automated collection pipeline.
The RAGDOLL dataset is from the paper Ranking Manipulation for Conversational Search Engines from Samuel Pfrommer, Yatong Bai, Tanmay Gautam, and Somayeh Sojoudi. For experiment code associated with this paper, please refer to this repository.
The dataset consists of 10… See the full description on the dataset page: https://huggingface.co/datasets/Bai-YT/RAGDOLL.RAG-Evaluation-Dataset-KO
Allganize RAG Leaderboard
Allganize RAG 리더보드는 5개 도메인(금융, 공공, 의료, 법률, 커머스)에 대해서 한국어 RAG의 성능을 평가합니다.일반적인 RAG는 간단한 질문에 대해서는 답변을 잘 하지만, 문서의 테이블과 이미지에 대한 질문은 답변을 잘 못합니다.
RAG 도입을 원하는 수많은 기업들은 자사에 맞는 도메인, 문서 타입, 질문 형태를 반영한 한국어 RAG 성능표를 원하고 있습니다.평가를 위해서는 공개된 문서와 질문, 답변 같은 데이터 셋이 필요하지만, 자체 구축은 시간과 비용이 많이 드는 일입니다.이제 올거나이즈는 RAG 평가 데이터를 모두 공개합니다.
RAG는 Parser, Retrieval, Generation 크게 3가지 파트로 구성되어 있습니다.현재, 공개되어 있는 RAG 리더보드 중, 3가지 파트를 전체적으로 평가하는 한국어로 구성된 리더보드는 없습니다.
Allganize RAG 리더보드에서는 문서를… See the full description on the dataset page: https://huggingface.co/datasets/allganize/RAG-Evaluation-Dataset-KO.RAG-Evaluation-Dataset-JA
Allganize RAG Leaderboard とは
Allganize RAG Leaderboard は、5つの業種ドメイン（金融、情報通信、製造、公共、流通・小売）において、日本語のRAGの性能評価を実施したものです。一般的なRAGは簡単な質問に対する回答は可能ですが、図表の中に記載されている情報などに対して回答できないケースが多く存在します。RAGの導入を希望する多くの企業は、自社と同じ業種ドメイン、文書タイプ、質問形態を反映した日本語のRAGの性能評価を求めています。RAGの性能評価には、検証ドキュメントや質問と回答といったデータセット、検証環境の構築が必要となりますが、AllganizeではRAGの導入検討の参考にしていただきたく、日本語のRAG性能評価に必要なデータを公開いたしました。RAGソリューションは、Parser、Retrieval、Generation の3つのパートで構成されています。現在、この3つのパートを総合的に評価した日本語のRAG Leaderboardは存在していません。（公開時点）Allganize RAG… See the full description on the dataset page: https://huggingface.co/datasets/allganize/RAG-Evaluation-Dataset-JA.Distillation_RAGpolicy-rag-corpus-metadata
Policy RAG Corpus Metadata (No Raw Data)
This repository is a metadata-only companion for the Policy RAG project built for the Quantic MSSE AI Engineering program.
It does not include the actual PDF files. The source PDFs are hosted in the companion GitHub repository.
What this repo includes
metadata.csv: structured metadata for 11 policy documents (filename, title, category, page count, source type, description)
Citation and provenance notes for reproducibility… See the full description on the dataset page: https://huggingface.co/datasets/mihai-chindris/policy-rag-corpus-metadata.kor-rag-opentestrag-qa-logs-corpus-data
🧠📚 RAG QA Logs & Corpus (Synthetic)
🧪 Multi-table synthetic RAG telemetry for quality, hallucinations, latency, and cost
A production-style, privacy-safe synthetic dataset that mimics telemetry exported from a real RAG system — from corpus → chunks → retrieval events → eval runs.
✅ Fully synthetic (no real users / orgs / PII).
⚡ Quick facts
Total rows: 103,255 across 6 linked tables
Labels (in eval_runs): is_correct, hallucination_flag, faithfulness_label… See the full description on the dataset page: https://huggingface.co/datasets/tarekmasryo/rag-qa-logs-corpus-data.SciBench-TruthfulQA-RAGrage_nq
RAGE - Retrieval Augmented Generation Evaluation
TL;DR
RAGE is a tool for evaluating how well Large Language Models (LLMs) cite relevant sources in Retrieval Augmented Generation (RAG) tasks.
More Details
For more information, please refer to our GitHub page:https://github.com/othr-nlp/rage_toolkit
References
This dataset is based on the BeIR version of the Natural Questions dataset.
BeIR:
Paper: https://doi.org/10.48550/arXiv.2104.08663… See the full description on the dataset page: https://huggingface.co/datasets/othr-nlp/rage_nq.preguntas-respuestas-RAGturkish-legal-rag
Turkish Legal RAG Corpus — Türk Hukuku için Açık RAG Datasetı
Tek cümle: 25 önemli Türk kanununun (mevzuat.gov.tr kaynaklı, madde bazlı temiz chunk'lar) + 290 manuel doğrulanmış soru-cevap altın benchmark'ının olduğu açık kaynak Türkçe hukuk RAG datasetı.
🇹🇷 Türkçe Özet — Bu dataset, Türkçe hukuk uygulamaları için sıfırdan üretilmiş açık ve denetlenebilir bir RAG corpus'udur. mevzuat.gov.tr üzerinden alınan 25 ana kanunun madde madde temizlenmiş, chunk'lanmış sürümünü (6.350… See the full description on the dataset page: https://huggingface.co/datasets/mtntasci/turkish-legal-rag.urdu_rag_dataset.csv
Dataset Card for Urdu RAG Knowledge Base
Dataset Overview
This dataset is designed specifically to bootstrap and evaluate Retrieval-Augmented Generation (RAG) applications, search systems, and semantic retrieval pipelines using the Urdu language. It contains 185 clean, structured, and informative text chunks covering a wide array of domains.
Language: Urdu (ur)
Script: Nastaliq / Arabic script (Unicode UTF-8)
Total Rows: 185 chunks
Format: CSV (id, title… See the full description on the dataset page: https://huggingface.co/datasets/fatymahaly/urdu_rag_dataset.csv.rage_hotpotqa
RAGE - Retrieval Augmented Generation Evaluation
TL;DR
RAGE is a tool for evaluating how well Large Language Models (LLMs) cite relevant sources in Retrieval Augmented Generation (RAG) tasks.
More Details
For more information, please refer to our GitHub page:https://github.com/othr-nlp/rage_toolkit
References
This dataset is based on the BeIR version of the HotpotQA dataset.
BeIR:
Paper: https://doi.org/10.48550/arXiv.2104.08663
HotpotQA:… See the full description on the dataset page: https://huggingface.co/datasets/othr-nlp/rage_hotpotqa.rag_thai_laws
Thai Laws Dataset
This dataset contains Thai law texts from the Office of the Council of State, Thailand.
The dataset has been cleaned and processed by the iApp Team to improve data quality and accessibility. The cleaning process included:
Converting system IDs to integer format
Removing leading/trailing whitespace from titles and text
Normalizing newlines to maintain consistent formatting
Removing excessive blank lines
The cleaned dataset is now available on Hugging Face for easy… See the full description on the dataset page: https://huggingface.co/datasets/iapp/rag_thai_laws.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.BiomixQA
BiomixQA Dataset
Overview
BiomixQA is a curated biomedical question-answering dataset comprising two distinct components:
Multiple Choice Questions (MCQ)
True/False Questions
This dataset has been utilized to validate the Knowledge Graph based Retrieval-Augmented Generation (KG-RAG) framework across different Large Language Models (LLMs). The diverse nature of questions in this dataset, spanning multiple choice and true/false formats, along with its coverage of various… See the full description on the dataset page: https://huggingface.co/datasets/kg-rag/BiomixQA.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.cs50-educational-rag
CS50 Pedagogical RAG Dataset
📜 Dataset Description
This repository contains the data artifacts for the undergraduate thesis, which explores the use of a pedagogical chatbot with Retrieval-Augmented Generation (RAG) for Harvard's CS50: Introduction to Computer Science course.
The project involved several stages of data processing, from raw content collection to the generation and curation of a high-quality evaluation dataset. To ensure full transparency and… See the full description on the dataset page: https://huggingface.co/datasets/dev-jonathanb/cs50-educational-rag.wiki_rag_testprivacy-preserving-real-world-human-motion-sample
Privacy-Preserving Real-World Human Motion Sample
A market-validation sample of anonymous 2D skeleton/pose observations derived from a real-world indoor CCTV stream.
Why this sample exists
We are validating demand for continuously collected, privacy-oriented real-world human-motion data before expanding to multi-camera releases.
Current public sample
750 public observations
derived pose/skeleton data
anonymous track identifiers
no raw RGB video
no… See the full description on the dataset page: https://huggingface.co/datasets/Ragab-Adel/privacy-preserving-real-world-human-motion-sample.RAG_Evaluation_Datasetturkuaz-rag
Turkuaz-RAG: A Novel Turkish Multi-Context Retrieval Benchmark
Turkuaz-RAG is the first benchmark specifically created for evaluating multi-context retrieval tasks in Turkish. It addresses a major gap in low-resource language research by providing multi-context questions, answers, and corresponding contexts.
Description of Benchmark
Languages: Turkish
Size: ~2,500 triplets (question, contexts, answer)
Context Sources: Turkish news articles from MLSUM
Question Types:… See the full description on the dataset page: https://huggingface.co/datasets/eneSadi/turkuaz-rag.MNLP_M3_rag_documentsRAGPPI
RAG Benchmark for Protein-Protein Interactions (RAGPPI)
📊 Overview
Retrieving expected therapeutic impacts in protein-protein interactions (PPIs) is crucial in drug development, enabling researchers to prioritize promising targets and improve success rates. While Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) frameworks accelerate discovery, no benchmark exists for identifying therapeutic impacts in PPIs.
RAGPPI is the first factual QA benchmark… See the full description on the dataset page: https://huggingface.co/datasets/Youngseung/RAGPPI.TuluEng100
TuluEng100
TuluEng100 is a dataset consisting of 100 sentence pairs of basic Tulu sentences along with its English translations. This is a smaller preview of our large data corpus that we are using for building the flagship model here at TuluAI.
What is the purpose of TuluEng100?
We want people to experiment and play around with TuluEng100. While we understand that it is not enough to train a model, we do want to see what is possible with just 100 sentence… See the full description on the dataset page: https://huggingface.co/datasets/ragumuddumane/TuluEng100.swiss-building-law-rag-bench
Swiss Cantonal Building Law RAG Benchmark
Evaluation benchmark for Retrieval-Augmented Generation (RAG) systems on Swiss cantonal
building law documents. Created as part of a bachelor thesis on systematic RAG pipeline
optimisation for German legal text.
Dataset contents
File
Entries
Language
Description
data/german/golden_dataset.jsonl
318
DE
German Q&A pairs grounded to article-level passages
data/multilingual/golden_dataset.jsonl
270
DE/FR/IT… See the full description on the dataset page: https://huggingface.co/datasets/MarcoFurrer/swiss-building-law-rag-bench.RAG_vs_FineTuning_Comparison_Persian_V2legal-rag-positives-synthetic
Synthetic QnA Chunk Pairs from Legal Documents
This dataset contains excerpts from legal cases' court opinions that mention artificial intelligence, along with corresponding question-answer pairs derived from the content. The data was sourced from CourtListener's public API and processed to create a structured dataset suitable for question-answering tasks.
Specifically including cases:
Senetas Corporation, Ltd. v. DeepRadiology Corporation
Electronic Privacy Information Center v.… See the full description on the dataset page: https://huggingface.co/datasets/AdamLucek/legal-rag-positives-synthetic.HealthcareMagic-RAGThis dataset undergone a comprehensive data augmentation pipeline to curate specifically for semantic retrieval and knowledge compactness.
MNLP_M2_rag_dataset