datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
XSTest
XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models
XSTest is a test suite designed to identify exaggerated safety / false refusal in Large Language Models (LLMs).
It comprises 250 safe prompts across 10 different prompt types, along with 200 unsafe prompts as contrasts.
The test suite aims to evaluate how well LLMs balance being helpful with being harmless by testing if they unnecessarily refuse to answer safe prompts that superficially… See the full description on the dataset page: https://huggingface.co/datasets/Paul/XSTest.XSTest
XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models
XSTest is a test suite designed to identify exaggerated safety / false refusal in Large Language Models (LLMs).
It comprises 250 safe prompts across 10 different prompt types, along with 200 unsafe prompts as contrasts.
The test suite aims to evaluate how well LLMs balance being helpful with being harmless by testing if they unnecessarily refuse to answer safe prompts that superficially… See the full description on the dataset page: https://huggingface.co/datasets/kevin-giskard/XSTest.APTO-XSTest-JA
APTO-XSTest-JA
APTO-XSTest-JA is a Japanese translated and annotated version of the XSTest dataset for AI safety evaluation research.
XSTest is a test suite designed to identify exaggerated safety behaviours in large language models, including cases where models refuse clearly safe prompts because they contain sensitive wording or resemble unsafe requests.
This dataset includes:
Japanese translations of XSTest prompts
Japanese refusal / non-refusal reference responses
Refusal… See the full description on the dataset page: https://huggingface.co/datasets/APTO-001/APTO-XSTest-JA.XSTest-In-Character-Refusals
🎭 In-Character Safety & Alignment Dataset (XSTest-Based)
Dataset Summary
This dataset is designed to train Large Language Models to maintain strict persona adherence during roleplay, even when responding to tricky, unsafe, or out-of-domain prompts.
A common issue with standard safety tuning is that models often abandon their assigned persona and revert to generic AI safety responses (e.g., "As an AI language model, I cannot..."). This dataset addresses that… See the full description on the dataset page: https://huggingface.co/datasets/mahdieh-sjp/XSTest-In-Character-Refusals.RU_XSTest