Provable Limits and Certified Deferral for Verbalized Uncertainty in Small Language Models

arXiv:2608.05064 · cs.CL, cs.AI, cs.LG · Submitted 2026-08-05 · Read on arXiv

Jianru Shen

cs.CL, cs.AI, cs.LG

Submitted: 2026-08-05

Comments: Accepted at MIWAI 2026 (The 19th International Conference on Multi-disciplinary Trends in Artificial Intelligence), to appear in Springer LNAI

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Calibration — 62× in this paper · explained in 9 episodes
• Deferral — 24× in this paper · explained in 2 episodes
• Accuracy — 18× in this paper · explained in 1 episode
• AUROC — 9× in this paper · explained in 3 episodes
• Selective Prediction — 4× in this paper · explained in 2 episodes
• Benchmark — 3× in this paper · explained in 2 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Distribution Shift — 2× in this paper · explained in 12 episodes
• Monotonicity — 2× in this paper · explained in 2 episodes
• Abstention — 1× in this paper · explained in 1 episode
• Confidence Calibration — 1× in this paper · explained in 2 episodes
• Conformal Prediction — 1× in this paper · explained in 11 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Edge Devices — 1× in this paper · explained in 2 episodes
• Empirical Coverage — 1× in this paper · explained in 2 episodes
• Expected Calibration Error — 1× in this paper
• Failure Modes — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Hallucination — 1× in this paper · explained in 4 episodes
• Human-in-the-loop — 1× in this paper · explained in 4 episodes
• Quantization — 1× in this paper · explained in 15 episodes
• Robustness — 1× in this paper · explained in 6 episodes
• Self-Consistency — 1× in this paper · explained in 3 episodes

Sources

• Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
• Language Models (Mostly) Know What They Know

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