datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
causalphys
Causal-VL Dataset
Causal reasoning VQA dataset with 4 categories × 4 subcategories (3062 questions).
Structure
Each subcategory contains:
annotations/*.json — question, answer, causal graph
data/ — images (.jpg/.png) or videos (.mp4)
Categories
Category
Subcategories
Perception
optics, containability, Scene_Reconstruction, Mechanics_Reasoning
Anticipation
Collision_Prediction, deformation, Fluid_Flow, Intention_Speculation
Intervention… See the full description on the dataset page: https://huggingface.co/datasets/haorentang/causalphys.medical_meadow_pubmed_causal
Dataset Card for Pubmed Causal
Dataset Summary
This is the dataset used in the paper: Detecting Causal Language Use in Science Findings.
Citation Information
@inproceedings{yu-etal-2019-detecting,
title = "Detecting Causal Language Use in Science Findings",
author = "Yu, Bei and
Li, Yingya and
Wang, Jun",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint… See the full description on the dataset page: https://huggingface.co/datasets/medalpaca/medical_meadow_pubmed_causal.CausalReasoningBenchmark
Automated Causal Reasoning Benchmark
Overview
The Automated Causal Reasoning Benchmark is a collection of real-world causal inference tasks drawn from 85 peer-reviewed research papers and three textbook-style collections (see CausalBenchmark.pdf). The benchmark contains 173 queries over 138 datasets. Each task is designed to evaluate both (i) identification, i.e., selecting an appropriate causal estimand and identification strategy given the study context, and (ii)… See the full description on the dataset page: https://huggingface.co/datasets/syrgkanislab/CausalReasoningBenchmark.Causal-Reasoning-Bench_CRBench
🦙 Causal Reasoning Benchmark (CRBench)
CRBench is a benchmark for evaluating process-level causal failures in
Chain-of-Thought (CoT) reasoning.
Rather than treating incorrect reasoning traces as homogeneous failures,
CRBench characterizes erroneous dependencies among intermediate reasoning
steps through a step-level causal-error taxonomy. It is designed to evaluate
whether reasoning methods can identify and correct structured causal failures
that arise during the reasoning… See the full description on the dataset page: https://huggingface.co/datasets/EdmondFU/Causal-Reasoning-Bench_CRBench.CausalBN-Bench
CausalBN-Bench Dataset
This dataset package contains the benchmark assets for CausalBN-Bench: A Comprehensive Benchmark for Causal Learning Capability of LLMs.
CausalBN-Bench evaluates large language models on Bayesian-network-based causal learning tasks:
Correlation identification
Causal skeleton identification
Causality identification
Contents
data/source_networks_and_labels/: raw Bayesian network files and ground-truth labels.… See the full description on the dataset page: https://huggingface.co/datasets/IEEERainy/CausalBN-Bench.Causal-Intervention-Tests-For-Explanation-Faithfulness
Faithfulness via Causal Interventions — Evaluation Pipeline
Paper: What Does Answer Change Rate Actually Measure? A Specificity Audit
of Causal Intervention Tests for Explanation Faithfulness
Accepted at: EMNLP 2026 Workshop GroundLM, Budapest, Hungary (emnlp.org)
This pipeline implements the causal-intervention evaluation for LLM
explanation faithfulness described in the accompanying paper, including two
controls: a content-free specificity check and a decoding-noise floor.… See the full description on the dataset page: https://huggingface.co/datasets/durgesh-rao/Causal-Intervention-Tests-For-Explanation-Faithfulness.domain-agnostic-causal-reasoning-tuning
Domain-Agnostic Causal Reasoning Tuning Dataset
Training data for fine-tuning language models on multi-hop document reasoning. Each example is a graded reasoning trace produced by a frontier AI agent solving a procedurally generated challenge from the Botcoin proof-of-inference network.
The traces contain no real domain knowledge. Entities are fictional, numbers are random, and documents are generated deterministically from 128-bit seeds. The reasoning structure is what matters:… See the full description on the dataset page: https://huggingface.co/datasets/botcoinmoney/domain-agnostic-causal-reasoning-tuning.compositional_causal_reasoning
– 3k+ Hugging Face downloads –
https://jmaasch.github.io/ccr/
Causal reasoning and compositional reasoning are two core aspirations in AI. Measuring these behaviors requires principled
evaluation methods. Maasch et al. (2025) consider both behaviors simultaneously, under
the umbrella of compositional causal reasoning (CCR): the ability to infer how causal measures compose and, equivalently, how causal quantities propagate
through graphs. CCR.GB applies the… See the full description on the dataset page: https://huggingface.co/datasets/jmaasch/compositional_causal_reasoning.CausalT5K
CausalT5K (clean export)
Deduplicated, evaluation-ready JSON for CausalT5K: a benchmark for diagnosing causal reasoning in LLMs (skepticism, sycophancy, detection–correction gap, rung collapse).
GitHub: genglongling/CausalT5kBench
Paper: arXiv:2602.08939
Files
File
Unique cases
Pearl level
CausalT5K_L1_clean.json
743
Association (L1)
CausalT5K_L2_clean.json
3,302
Intervention (L2), full deduplicated export
CausalT5K_L2_clean_small.json
1,360… See the full description on the dataset page: https://huggingface.co/datasets/GloriaGeng/CausalT5K.CausalDriveBench
CausalDriveBench
A benchmark for causal reasoning in autonomous driving built on top of
nuScenes. Each sample bundles a curated
causal scene graph, three flavours of multiple-choice / open-ended QA
(active, dormant, distractor), and pointers to the raw nuScenes frames so the
benchmark stays compact and license-clean.
At a glance
Subset uploaded: nuscenes
Samples: 815 across 475 scenes
Tasks: active QA, dormant QA, distractor QA, causal scene graphs
Folder… See the full description on the dataset page: https://huggingface.co/datasets/causaldrivebench/CausalDriveBench.CausalCrash
CausalCrash Dataset
A Hierarchical Benchmark for Evaluating Counterfactual Reasoning in Road Safety Scenarios
Overview
CausalCrash is a hierarchical benchmark designed to evaluate counterfactual and causal reasoning in road safety scenarios. The dataset focuses on real-world crash and near-miss events, enabling research in temporal reasoning, causal inference, and multimodal video understanding.
Key Features
Real-world driving scenarios (crashes… See the full description on the dataset page: https://huggingface.co/datasets/meet2008/CausalCrash.causal_arc
★ 1k+ Hugging Face downloads ★
★ NeurIPS 2025 LAW Workshop – Spotlight Paper ★
★ Amazon AGI Trusted AI Symposium 2026 – Poster ★
Official project page: https://jmaasch.github.io/carc/
Overview
On-the-fly reasoning often requires adaptation to novel problems under limited data and distribution shift.
This work introduces CausalARC: an experimental testbed for AI reasoning in low-data and out-of-distribution regimes,
modeled after the… See the full description on the dataset page: https://huggingface.co/datasets/jmaasch/causal_arc.CausalReasoningBenchmark
Automated Causal Reasoning Benchmark
Anonymized release for double-blind review. Author, affiliation, and prior-whitepaper material have been removed. The data, solutions, and evaluation pipeline are otherwise identical to the version under review.
Overview
The Automated Causal Reasoning Benchmark is a collection of real-world causal inference tasks drawn from 85 peer-reviewed research papers and three textbook-style collections. The benchmark contains 173 queries over… See the full description on the dataset page: https://huggingface.co/datasets/anonsubmission16/CausalReasoningBenchmark.causal_kg_eval
Logic-Aware Causal Knowledge Graph Dataset
이 데이터셋은 비구조화된 텍스트에서 추출된 논리적 관계와 인과 경로의 타당성을 평가하기 위해 설계되었습니다. 단순한 유사도 기반 검색을 넘어, 구조화된 지식을 활용한 고난도 추론 성능 측정을 목적으로 합니다.
1. 개요 (Overview)
목적: 정보 간의 선후 관계, 인과성 및 다단계(Multi-hop) 연결성 검증
데이터 형식: JSON (head, relation, tail)
핵심 기능: Semantic Noise 필터링 및 논리적 추론 경로(Reasoning Path) 제공
2. 관계 스키마 (Relation Schema)
본 데이터셋은 정보 간의 연결 강도와 성격에 따라 다음 4가지 관계를 정의합니다.
Taxonomy (is_a): 상위 개념과 하위 개념 간의 계층적 분류
Causality (cause_of): 명확한 방향성을 가진… See the full description on the dataset page: https://huggingface.co/datasets/crjojo/causal_kg_eval.Retrieval-SFT-Chat
Retrieval-Based Multi-Turn Chat SFT Synthetic Data
A year ago, we released CausalLM/Refined-Anime-Text, a thematic subset of a dataset generated using the then state-of-the-art LLMs. This dataset comprises 1 million entries synthesized through long-context models that rewrote multi-document web text inputs, intended for continued pre-training. We are pleased to note that this data has been employed in various training scenarios and in studies concerning data and internet culture.
In… See the full description on the dataset page: https://huggingface.co/datasets/CausalLM/Retrieval-SFT-Chat.CausalDiagnosticity
A Causal Lens for Evaluating Faithfulness Metrics
paper | code
Authors: Kerem Zaman and Shashank Srivastava
This dataset was created to evaluate faithfulness metrics using four controlled tasks: (1) fact-checking, (2) analogy, (3) object counting, and (4) multi-hop reasoning. These tasks assess causal diagnosticity by using counterfactual models with faithful and unfaithful explanations. They are deliberately designed to span varying levels of complexity. The Fact Check task is the… See the full description on the dataset page: https://huggingface.co/datasets/l3-unc/CausalDiagnosticity.causal_factors
Causal Factors Dataset
This dataset provides 'causal factors' for each sample in MMLU, BIG-Bench Hard (BBH) (specifically, the thirteen problem subset used in Turpin et al., 2023), and GPQA (specifically, GPQA Diamond). We use this dataset to test for the faithfulness and verbosity of models' chain of thought reasoning, to better understand how we can measure monitorability.
For each problem in these constituent datasets, we use a panel of judge models to extract any factors that… See the full description on the dataset page: https://huggingface.co/datasets/ameek/causal_factors.