Probability is Not Enough: Exploring and Counting Divergent Tokens for Reasoning Uncertainty Quantification in LLMs
cs.AI
Submitted: 2026-09-29
Updated: 2026-09-29
Code: https://github.com/szu-tera/DTC
Terminology
Sources
- DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
- From Calibration to Collaboration: LLM Uncertainty Quantification Should Be More Human-Centered
- Gemma 3 Technical Report
- Cross-Model Disagreement as a Label-Free Correctness Signal
- OpenAI o1 System Card
- Qwen2.5 Technical Report
- CrossCheckGPT: Universal Hallucination Ranking for Multimodal Foundation Models
- Let the Model Distribute Its Doubt: Confidence Estimation through Verbalized Probability Distribution
- A Systematic Evaluation of Black-Box Uncertainty Estimation Methods for Large Language Models
- Qwen3 Technical Report
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems