Verbalized and Internal Probabilities Are Coupled in Large Language Models

arXiv:2610.00827 · cs.CL, cs.AI · Submitted 2026-09-30 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-09-30

Updated: 2026-09-30

Terminology

• Alignment — 33× in this paper · explained in 1 episode
• Transformer — 15× in this paper · explained in 2 episodes
• Calibration — 8× in this paper · explained in 7 episodes
• Empirical Methods in Natural Language Processing — 4× in this paper
• Fine-Tuning — 4× in this paper · explained in 5 episodes
• Generalization — 3× in this paper · explained in 13 episodes
• Generative AI — 3× in this paper · explained in 2 episodes
• Latent Representation — 3× in this paper · explained in 2 episodes
• Adam — 2× in this paper · explained in 2 episodes
• Hallucination — 2× in this paper · explained in 3 episodes
• In-Context Learning — 2× in this paper · explained in 4 episodes
• Accountability — 1× in this paper · explained in 2 episodes
• Actor — 1× in this paper · explained in 3 episodes
• AdamW Optimizer — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Direct Preference Optimization (DPO) — 1× in this paper · explained in 9 episodes
• EMMA — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• In-Context Learning (ICL) — 1× in this paper · explained in 5 episodes
• Steering — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• LM-Polygraph: Uncertainty Estimation for Language Models
• Language Models (Mostly) Know What They Know
• Interactive Model with Structural Loss for Language-based Abductive Reasoning
• Teaching Models to Express Their Uncertainty in Words
• 2 OLMo 2 Furious
• LLM Processes: Numerical Predictive Distributions Conditioned on Natural Language
• Gemma 2: Improving Open Language Models at a Practical Size
• Uncertainty Propagation in LLM-Based Systems
• Qwen3 Technical Report
• Qwen2.5 Technical Report
• Direct Confidence Alignment: Aligning Verbalized Confidence with Internal Confidence In Large Language Models
• When Linguistic and Internal Confidence Diverge in 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