Learning To See But Forgetting To Follow: Visual Instruction Tuning Makes LLMs More Prone To Jailbreak Attacks

Code & data for our paper accepted to Safety4ConvAI workshop in LREC/COLING 2024

Name		Name	Last commit message	Last commit date
Latest commit History 213 Commits
annotations		annotations
data		data
internlm2		internlm2
llava		llava
plots		plots
predictions		predictions
qwen		qwen
vicuna		vicuna
.editorconfig		.editorconfig
.gitignore		.gitignore
README.md		README.md
dataset_iterator.py		dataset_iterator.py
gradio-keyboard.js		gradio-keyboard.js
gradio_annotation.py		gradio_annotation.py
requirements.txt		requirements.txt

Provide feedback