Is Discrete Difficulty Sufficient? Leveraging Continuous Difficulty for Efficient Self-Consistency in LLMs
cs.CL
Submitted: 2026-08-25
Updated: 2026-08-25
Terminology
Sources
- Gemma 3 Technical Report
- Scaling Laws for Neural Language Models
- Probing the Difficulty Perception Mechanism of Large Language Models
- Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step Reasoning
- Measuring Mathematical Problem Solving With the MATH Dataset
- DiffAdapt: Difficulty-Adaptive Reasoning for Token-Efficient LLM Inference
- Training Compute-Optimal Large Language Models
- GPQA: A Graduate-Level Google-Proof Q&A Benchmark
- Proximal Policy Optimization Algorithms
- A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- A Survey of Large Language Models
- Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
- Enhancing Safety of Large Language Models via Embedding Space Separation
- Less is More Tokens: Efficient Math Reasoning via Difficulty-Aware Chain-of-Thought Distillation
- Self-Consistency Improves Chain of Thought Reasoning in Language Models
- Qwen2.5 Technical Report
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