LOCKR: A Hidden-State Trajectory-Guided Planner for Detecting and Repairing Stable-but-Wrong Lock-In in Diffusion Language Models

arXiv:2609.27220 · cs.CL · Submitted 2026-09-23 · Read on arXiv

cs.CL

Submitted: 2026-09-23

Updated: 2026-09-24

Terminology

• Accuracy — 89× in this paper · explained in 1 episode
• AUROC — 40× in this paper · explained in 2 episodes
• Benchmark — 37× in this paper · explained in 2 episodes
• Verifier — 32× in this paper · explained in 2 episodes
• AUC — 16× in this paper · explained in 2 episodes
• Ablation — 14× in this paper · explained in 1 episode
• Verification — 13× in this paper · explained in 2 episodes
• Hallucination — 7× in this paper · explained in 4 episodes
• Diffusion Model — 5× in this paper · explained in 8 episodes
• Consistency — 4× in this paper · explained in 3 episodes
• Diffusion Models — 4× in this paper · explained in 6 episodes
• Hallucination Detection — 4× in this paper · explained in 2 episodes
• Calibration — 3× in this paper · explained in 7 episodes
• Self-consistency — 3× in this paper · explained in 2 episodes
• Aggregation — 2× in this paper · explained in 1 episode
• Iterative Refinement — 2× in this paper · explained in 3 episodes
• Regularization — 2× in this paper · explained in 3 episodes
• Test-time Scaling — 2× in this paper · explained in 2 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Block Diffusion — 1× in this paper · explained in 2 episodes
• Causal Inference — 1× in this paper · explained in 4 episodes
• Chain-of-Thought Prompting — 1× in this paper · explained in 2 episodes
• Decode — 1× in this paper · explained in 2 episodes
• EMMA — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Hallucination Mitigation — 1× in this paper · explained in 2 episodes
• KV cache — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes

Sources

• LLaDA2.0: Scaling Up Diffusion Language Models to 100B
• Training Verifiers to Solve Math Word Problems
• Inference-Time Scaling of Diffusion Language Models via Trajectory Refinement
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• DiffusionGemma Technical Report
• Language Models (Mostly) Know What They Know
• dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching
• Orca-Math: Unlocking the potential of SLMs in Grade School Math
• Large Language Diffusion Models
• Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding
• Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement
• Dream 7B: Diffusion Large Language Models
• The Lessons of Developing Process Reward Models in Mathematical Reasoning
• HIVE: Hidden-Evidence Verification for Hallucination Detection in Diffusion Large Language Models
• ProcessBench: Identifying Process Errors in Mathematical Reasoning

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