git clone https://github.com/96kihyun/batch_jailbreak.git
cd batch_jailbreak

conda create -n batch python=3.10 -y
conda activate batch
pip install -r requirements.txt

python -m src.utils.generate_batch_question_prompt

python scripts/inference/run_inference_batch_prompt.py \
  --model_name qwen \
  --case single_math --n 9 --pos 2 \
  --harmful_dataset JBB

bash scripts/inference/run_inference_batch_prompt_eval.sh \
  --dataset jbb --gpu_id 0 \
  --models phi qwen --cases single_math \
  --batch_sizes 12 --pos_values 1 2

python scripts/inference/run_inference_api.py \
  --api gpt \
  --input_file data/batch_prompt_jbb/single_math/12/pos_2.jsonl \
  --model_name gpt --output_subdir batch_prompt_jbb/single_math/12/pos_2 \
  --harmful_dataset JBB --extract_pos 2

python scripts/eval/run_ensemble.py \
  --input_file result/inference/qwen/batch_prompt_jbb/single_math/12/qwen_single_math_n12_pos_2_response.jsonl \
  --output_dir result/evaluation/batch_prompt_jbb/qwen/single_math/12/pos_2

bash scripts/inference/run_inference_batch_prompt_eval.sh \
  --dataset jbb --gpu_id 0 \
  --models qwen --cases single_math \
  --batch_sizes 12 --pos_values 2 \
  --conda_env batch

# 1. data
python -m src.utils.generate_batch_question_prompt \
  --harmful_dataset JBB --min_n 12 --max_n 12 --num_samples 100

# 2. inference
python scripts/inference/run_inference_batch_prompt.py \
  --model_name llama --case single_math --n 12 --pos 2 --harmful_dataset JBB

# 3. evaluation
python scripts/eval/run_ensemble.py \
  --input_file result/inference/llama/batch_prompt/llama_single_math_n12_pos_2_response.jsonl

@article{kim2026safety,
  title={Safety in Batches? Understanding and Mitigating Safety Failures in Batch Prompting},
  author={Kim, Kihyun and Kim, HeeSeon and Lee, Wonjun and Kim, Changick},
  journal={arXiv preprint arXiv:2608.02681},
  year={2026}
}