Where Is Uncertainty Observed? A Mechanistic Understanding of Uncertainty Quantification in LLMs
cs.CL, cs.AI, cs.LG
Submitted: 2026-11-11
Updated: 2026-11-11
Terminology
Sources
- Program Synthesis with Large Language Models
- Layer Normalization
- Uncertainty in Natural Language Generation: From Theory to Applications
- MS MARCO: A Human Generated MAchine Reading COmprehension Dataset
- Understanding AI from the Inside: The State of Mechanistic Interpretability for AI Safety
- Cycles of Thought: Measuring LLM Confidence through Stable Explanations
- Rethinking the Uncertainty: A Critical Review and Analysis in the Era of Large Language Models
- Eliciting Latent Predictions from Transformers with the Tuned Lens
- U-Space: Uncovering When and Why Uncertainty Arises in Language Models
- HalluSAE: Detecting Hallucinations in Large Language Models via Sparse Auto-Encoders
- MTBench: A Multimodal Time Series Benchmark for Temporal Reasoning and Question Answering
- Evaluating Large Language Models Trained on Code
- Uncertainty Quantification of Large Language Models through Multi-Dimensional Responses
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Training Verifiers to Solve Math Word Problems
- LLM Uncertainty Quantification through Directional Entailment Graph and Claim Level Response Augmentation
- DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
- UProp: Investigating the Uncertainty Propagation of LLMs in Multi-Step Agentic Decision-Making
- Toy Models of Superposition
- A Structured Review of Literature on Uncertainty in Machine Learning & Deep Learning
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data