MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment
cs.CL
Submitted: 2026-07-13
Updated: 2026-11-09
Terminology
Sources
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
- Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned
- TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards
- GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher
- CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models
- Jailbreak-R1: Exploring the Jailbreak Capabilities of LLMs via Reinforcement Learning
- Siren: A Learning-Based Multi-Turn Attack Framework for Simulating Real-World Human Jailbreak Behaviors
- Proximal Policy Optimization Algorithms
- Proximity-Based Multi-Turn Optimization: Practical Credit Assignment for LLM Agent Training
- Hierarchy-of-Groups Policy Optimization for Long-Horizon Agentic Tasks
- Qwen2 Technical Report
- The Llama 3 Herd of Models
- Gemma 2: Improving Open Language Models at a Practical Size
- Mistral 7B
- Qwen3Guard Technical Report
- Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
- Prefill-level Jailbreak: A Black-Box Risk Analysis of Large Language Models
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data