Certainty Is Not Just Correctness: Rethinking Token-Level Certainty in LLM Reasoning
cs.CL, cs.AI
Submitted: 2026-09-26
Updated: 2026-09-26
Code: https://github.com/WNJXYK/RPC
Terminology
Sources
- The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning
- MathArena: Evaluating LLMs on Uncontaminated Math Competitions
- How Well Does First-Token Entropy Approximate Word Entropy as a Psycholinguistic Predictor?
- Deep Think with Confidence
- Gemma 4 Technical Report
- Reasoning or Fluency? Dissecting Probabilistic Confidence in Best-of-N Selection
- Reliability-Aware Adaptive Self-Consistency for Efficient Sampling in LLM Reasoning
- Certainty-Guided Reasoning in Large Language Models: A Dynamic Thinking Budget Approach
- gpt-oss-120b & gpt-oss-20b Model Card
- Maximizing Confidence Alone Improves Reasoning
- Think Just Enough: Sequence-Level Entropy as a Confidence Signal for LLM Reasoning
- Confidence Improves Self-Consistency in LLMs
- Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
- Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning
- Qwen3 Technical Report
- Dynamic Early Exit in Reasoning 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