31 datasets found

The Comprehensive Assessment of Jailbreak Attacks against LLMs dataset is used to evaluate the effectiveness of jailbreak attacks on language models.

UMSE is a unified multi-scenario summarization evaluation framework that can perform semantic evaluation on three typical evaluation scenarios: Sum-Ref, Sum-Doc, and Sum-Doc-Ref...

A large dataset of text-to-image prompts for training and evaluation

The dataset used for pre-training language models, containing a large collection of text documents.

The Kodak True Color Image Suite is a dataset of images used for evaluating image compression algorithms.

The dataset used to evaluate the effectiveness of different jailbreak attack methods against LLMs. The dataset contains 160 forbidden questions with high diversity.

The dataset used in the paper to evaluate the effectiveness of different jailbreak attack methods against Large Language Models (LLMs).

The Do-Not-Answer dataset is designed to test the safety performance of Large Language Models (LLMs).

A dataset for evaluating geospatial foundation models

A dataset for evaluating the performance of text-to-image models, namely ViLG-300 and ParaPrompts-400.

A dataset for evaluating the performance of text-to-image models, namely ViLG-300 and ParaPrompts-400.