DoubtLess: Training-Free Contrastive Decoding for Efficient Reasoning
cs.CL, cs.AI, cs.LG
Submitted: 2026-10-13
Updated: 2026-10-13
Code: https://github.com/leoluolol/DoubtLess
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning
- PromptCD: Test-Time Behavior Enhancement via Polarity-Prompt Contrastive Decoding
- Evaluating Large Language Models Trained on Code
- Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
- Steer Model beyond Assistant: Controlling System Prompt Strength via Contrastive Decoding
- Nudging: Inference-time Alignment of LLMs via Guided Decoding
- Efficiently Scaling LLM Reasoning with Certaindex
- Measuring Mathematical Problem Solving With the MATH Dataset
- ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning
- EXAONE 4.0: Unified Large Language Models Integrating Non-reasoning and Reasoning Modes
- What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding
- Let's Verify Step by Step
- LACONIC: Length-Aware Constrained Reinforcement Learning for LLM
- O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning
- Reasoning Models Can Be Effective Without Thinking
- s1: Simple test-time scaling
- Contrastive Decoding Improves Reasoning in Large Language Models
- THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models
- The Benefits of a Concise Chain of Thought on Problem-Solving in Large Language Models
- Stop Overthinking: A Survey on Efficient Reasoning for Large Language 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