Temporally-Resolved Token Attribution Reveals the Generation Dynamics of Diffusion Language Models

arXiv:2610.01177 · cs.CL, cs.AI, cs.LG · Submitted 2026-10-01 · Read on arXiv

cs.CL, cs.AI, cs.LG

Submitted: 2026-10-01

Updated: 2026-10-01

Terminology

• AUC — 20× in this paper · explained in 2 episodes
• Accuracy — 8× in this paper · explained in 1 episode
• Integrated Gradients — 8× in this paper
• Interpretability — 8× in this paper · explained in 15 episodes
• Fine-Tuning — 7× in this paper · explained in 5 episodes
• Robustness — 7× in this paper · explained in 5 episodes
• Diffusion Model — 4× in this paper · explained in 8 episodes
• Steering — 4× in this paper · explained in 2 episodes
• Transformer — 4× in this paper · explained in 2 episodes
• Activation Patching — 3× in this paper · explained in 2 episodes
• Axioms — 3× in this paper · explained in 2 episodes
• Diffusion Layer Integrated Gradients — 3× in this paper
• Mechanistic interpretability — 3× in this paper · explained in 2 episodes
• Multi-hop Reasoning — 3× in this paper · explained in 3 episodes
• Adaptation — 2× in this paper · explained in 1 episode
• Benchmark — 2× in this paper · explained in 2 episodes
• Iterative Refinement — 2× in this paper · explained in 3 episodes
• Ontology — 2× in this paper · explained in 2 episodes
• Scaffolding — 2× in this paper · explained in 3 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Additive Decomposition — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Decode — 1× in this paper · explained in 2 episodes
• Diffusion Models — 1× in this paper · explained in 6 episodes
• Diffusion Processes — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Explainability — 1× in this paper · explained in 3 episodes
• Explainable AI (XAI) — 1× in this paper · explained in 7 episodes
• Latent Reasoning — 1× in this paper · explained in 2 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• Sparsity — 1× in this paper · explained in 4 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• The Attribution Contract for Generative Language Models
• TimeROME-DLM: Temporal Causal Tracing and Low-Rank Inference-Time Knowledge Editing for Masked Diffusion Language Models
• Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions
• The pitfalls of next-token prediction
• Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference
• FLARE: Diffusion for Hybrid Language Model
• Understanding intermediate layers using linear classifier probes
• Phonetic Perturbations Reveal Tokenizer-Rooted Safety Gaps in LLMs
• Diffusion Integrated Gradients: Controllable Path Generation for Flexible Feature Attribution
• Mechanistic Interpretability for AI Safety -- A Review
• Observable Patterns Are Not Explanations: A Causal-Geometric Analysis of Latent Reasoning Models
• ConceptGuard: Neuro-Symbolic Safety Guardrails via Sparse Interpretable Jailbreak Concepts
• Do Sparse Autoencoders Capture Concept Manifolds?
• Structuring Sparsity: Block-Sparse Featurizers Capture Visual Concept Manifolds
• Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior
• Activation Steering for Masked Diffusion Language Models
• DLM-SWAI: Steering Diffusion Language Models Before They Unmask
• Where Should Diffusion Enter a Language Model? Geometry-Guided Hidden-State Replacement
• Training Large Language Models to Reason in a Continuous Latent Space

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering