Uncertainty Localization in LLM Reasoning via Embedding Perturbations

arXiv:2602.02427 · cs.LG · Submitted 2026-02-02 · Read on arXiv

cs.LG

Submitted: 2026-02-02

Updated: 2026-10-05

Terminology

• Uncertainty Quantification — 2× in this paper · explained in 9 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes

Sources

• gpt-oss-120b & gpt-oss-20b Model Card
• Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Models
• Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantification
• Explaining and Harnessing Adversarial Examples
• Measuring Mathematical Problem Solving With the MATH Dataset
• Mistral 7B
• Language Models (Mostly) Know What They Know
• Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation
• Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback
• Self-Consistency Improves Chain of Thought Reasoning in Language Models
• Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs
• To Believe or Not to Believe Your LLM
• Qwen2 Technical Report
• Qwen3 Technical Report
• FreeLB: Enhanced Adversarial Training for Natural Language Understanding

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks