datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
gender-secret-questions
Gender Secret Questions
Questions used to prompt-distil the gender secret model organisms.
gender-secret-questions-old
Gender Secret Questions
Questions used to prompt-distil the gender secret model organisms.
aart-ai-safety-datasetunrelated-questions-follow-up-questions
Unrelated Questions — Follow-up Elicitation Questions
The fixed set of yes/no follow-up ("elicitation") questions used by the Unrelated
Questions lie detector, reproduced from
How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions
(Pacchiardi et al., ICLR 2024).
After a model produces a response, each question is appended as a new user message and the
model's yes/no logprobs are recorded. The per-question
logsumexp(yes_logprobs) -… See the full description on the dataset page: https://huggingface.co/datasets/ai-safety-institute/unrelated-questions-follow-up-questions.city_countries_well_knownAI-Safety_Reliability_ReseachReal-World Gaps in AI Governance Research
Github repository: https://github.com/ssrc-ai-disclosures/ai-governance-research
LLM-AI-Safety-Response-Classification
ASRCD — AI Safety Response Classification Dataset
Understanding AI Decision Making, Harm Detection, and Response Strategy in Real-World LLM Interactions
Author: Umair SaeedVersion: 1.0Total Rows: 1,000Format: CSVLanguage: EnglishTask Type: Multi-label Text ClassificationLicense: Research and Educational Use Only
About Dataset
ASRCD — AI Safety Response Classification Dataset
Overview
This dataset is designed to train and evaluate… See the full description on the dataset page: https://huggingface.co/datasets/umairpy/LLM-AI-Safety-Response-Classification.ai-5node-cost-buf-lag-cpl-cost-cut-safety-erosion-v0.1
What this repo does
This dataset models safety erosion cascades driven by cost pressure in AI operations. It detects when cost pressure rises, safety buffers weaken, governance lag grows due to thin staffing and delayed review, and tight coupling through shared pipelines and automation crosses the five-node cascade threshold into an unrecoverable safety erosion cascade.
This dataset models a five-node cascade: four interacting instability drivers and one emergent cascade state.The… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/ai-5node-cost-buf-lag-cpl-cost-cut-safety-erosion-v0.1.