Extracting Training Data from Diffusion Language Models via Infilling
cs.CL, cs.AI, cs.CR, cs.LG
Submitted: 2026-05-22
Updated: 2026-11-18
Project page: https://microsoft.github.io/presidio
Terminology
Sources
- LLaDA2.0: Scaling Up Diffusion Language Models to 100B
- LLaDA2.1: Speeding Up Text Diffusion via Token Editing
- Unlocking Prompt Infilling Capability for Diffusion Language Models
- Mercury: Ultra-Fast Language Models Based on Diffusion
- Tulu 3: Pushing Frontiers in Open Language Model Post-Training
- A Survey on Diffusion Language Models
- Characterizing Memorization in Diffusion Language Models: Generalized Extraction and Sampling Effects
- DynHD: Hallucination Detection for Diffusion Large Language Models via Denoising Dynamics Deviation Learning
- Balancing Innovation and Oversight: AI in the U.S. Treasury and IRS: A Survey
- Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference
- Self-conditioned Embedding Diffusion for Text Generation
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- Exploring Cross-Client Memorization of Training Data in Large Language Models for Federated Learning
- The Landscape of Memorization in LLMs: Mechanisms, Measurement, and Mitigation
- Dream 7B: Diffusion Large Language Models
- dLLM: Simple Diffusion Language Modeling
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