Safety in Batches? Understanding and Mitigating Safety Failures in Batch Prompting

arXiv:2608.02681 · cs.CR · Submitted 2026-08-03 · Read on arXiv

cs.CR

Submitted: 2026-08-03

Updated: 2026-09-11

Comments: jailbreak, safety

Code: https://github.com/tatsu-lab/stanford_alpaca

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Attack Success Rate — 13× in this paper
• Benchmark — 8× in this paper · explained in 2 episodes
• In-Context Learning — 8× in this paper · explained in 7 episodes
• Robustness — 8× in this paper · explained in 6 episodes
• Thinking mode — 7× in this paper · explained in 2 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Accuracy — 5× in this paper · explained in 1 episode
• Papers — 5× in this paper · explained in 3 episodes
• Trace — 4× in this paper · explained in 2 episodes
• Ablation Studies — 3× in this paper · explained in 1 episode
• Composition — 3× in this paper · explained in 2 episodes
• Generalization — 2× in this paper · explained in 14 episodes
• Low-Resource Languages — 2× in this paper · explained in 4 episodes
• Perplexity — 2× in this paper · explained in 3 episodes
• Reasoning Traces — 2× in this paper · explained in 4 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Ablation Study — 1× in this paper · explained in 3 episodes
• Benchmarking — 1× in this paper · explained in 4 episodes
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• F1 Score — 1× in this paper · explained in 4 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Gating Network — 1× in this paper · explained in 2 episodes
• Hyperparameters — 1× in this paper · explained in 2 episodes
• Korea Advanced Institute of Science and Technology — 1× in this paper
• Language Models (LLMs) — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 9 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Supervised Fine-Tuning — 1× in this paper
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 13 episodes
• Task Decomposition — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• Constitutional AI: Harmlessness from AI Feedback
• Training Verifiers to Solve Math Word Problems
• Phi-4 Technical Report
• Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy
• The Llama 3 Herd of Models
• Uncertainty-aware Reward Model: Teaching Reward Models to Know What is Unknown
• Baseline Defenses for Adversarial Attacks Against Aligned Language Models
• CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models
• RewardBench 2: Advancing Reward Model Evaluation
• Jailbreaking in the Haystack
• Qwen3 Technical Report

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Estimating the Social Cost of Corporate Data Breaches
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills