-
Context versus Prior Knowledge in Language Models
The dataset used in the paper to test the persuasion and susceptibility scores of language models. -
AdvBench dataset
The dataset used for the experiments in the paper, consisting of 60 harmful instructions from the AdvBench dataset. -
Multilingual Blending: LLM Safety Alignment Evaluation with Language Mixture
Multilingual Blending: LLM Safety Alignment Evaluation with Language Mixture -
Training Language Models to Perform Tasks
A dataset for training language models to perform tasks such as question answering and text classification.
