8 datasets found

A large language model that is significantly larger than the largest model tested in the results discussed above.

Realistic and controllable traffic simulation is a core capability that is necessary to accelerate autonomous vehicle (AV) development.

The dataset used in the paper to test the Gradient Cuff method for detecting jailbreak attacks on large language models.

The dataset used in the paper to test the Gradient Cuff method for detecting jailbreak attacks on large language models.

The dataset used in the paper to test the Gradient Cuff method for detecting jailbreak attacks on large language models.

Qsnail, the first dataset specifically constructed for the questionnaire generation task, comprises 13,168 human-written questionnaires gathered from online platforms.

The dataset used in this paper is the CodeT5 dataset, which is a code generation large language model.

The GELLA framework leverages a large language model to ground entities with long captions.