Towards Efficient Reasoning: Learning Causal Shortcuts for Diffusion Language Models
cs.CL
Submitted: 2026-09-23
Updated: 2026-09-23
Code: https://github.com/ZJUDianJin/CausalShortcuts-Learning
Terminology
Sources
- Program Synthesis with Large Language Models
- Evaluating Large Language Models Trained on Code
- DSFT: Inspiring Diffusion Large Language Models to Comprehend Mathematical and Logical Patterns
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Training Verifiers to Solve Math Word Problems
- Should We Still Pretrain Encoders with Masked Language Modeling?
- C$^2$DLM: Causal Concept-Guided Diffusion Large Language Models
- Measuring Massive Multitask Language Understanding
- Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions
- Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution
- GPQA: A Graduate-Level Google-Proof Q&A Benchmark
- Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability
- Blockwise SFT for Diffusion Language Models: Reconciling Bidirectional Attention and Autoregressive Decoding
- On the Reasoning Abilities of Masked Diffusion Language Models
- GIFT: Guided Importance-Aware Fine-Tuning for Diffusion Language Models
- Dream 7B: Diffusion Large Language Models
- LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models
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