Beyond the Prompt: Leveraging Pre-Decoding States for Jailbreak Detection in dLLMs
cs.CL, cs.CY, cs.LG
Submitted: 2026-11-06
Updated: 2026-11-06
Code: https://github.com/tatsu-lab/stanford_alpaca
Terminology
Sources
- Dream 7B: Diffusion Large Language Models
- Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference
- LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models
- Jailbreaking Large Language Diffusion Models: Revealing Hidden Safety Flaws in Diffusion-Based Text Generation
- Safer by Diffusion, Broken by Context: Diffusion LLM's Safety Blessing and Its Failure Mode
- The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets
- HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
- Prefill-level Jailbreak: A Black-Box Risk Analysis of Large Language Models
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Program Synthesis with Large Language Models
- Gemma 3 Technical Report
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