A Robust Evaluation of Probe Robustness: Lessons for Reliable OOD Uncertainty Quantification

arXiv:2604.11662 · cs.CL · Submitted 2026-04-13 · Read on arXiv

cs.CL

Submitted: 2026-04-13

Updated: 2026-08-30

Terminology

• Robustness — 64× in this paper · explained in 5 episodes
• Uncertainty Quantification — 13× in this paper · explained in 8 episodes
• Aggregation — 11× in this paper · explained in 1 episode
• Hallucination — 10× in this paper · explained in 4 episodes
• Distribution Shift — 8× in this paper · explained in 6 episodes
• LLM-as-a-Judge — 7× in this paper · explained in 3 episodes
• Leave-one-out OOD — 7× in this paper
• Hybrid Back-Off — 5× in this paper
• Hallucination Detection — 4× in this paper · explained in 2 episodes
• Perplexity — 4× in this paper · explained in 3 episodes
• Transformer — 4× in this paper · explained in 2 episodes
• Verification — 3× in this paper · explained in 2 episodes
• AUC — 2× in this paper · explained in 2 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Linear probe — 2× in this paper · explained in 2 episodes
• Partial Least Squares — 2× in this paper
• Supervised Uncertainty Quantification — 2× in this paper
• Ablation — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 4 episodes
• Epistemic Uncertainty — 1× in this paper · explained in 10 episodes
• SATRMD with the Maximum Sequence Probability — 1× in this paper

Sources

• Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs
• Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation
• Confidence-Based Response Abstinence: Improving LLM Trustworthiness via Activation-Based Uncertainty Estimation
• RoBERTa: A Robustly Optimized BERT Pretraining Approach
• ReProbe: Efficient Test-Time Scaling of Multi-Step Reasoning by Probing Internal States of Large Language Models
• Real-Time Detection of Hallucinated Entities in Long-Form Generation
• HaluNet: Learning Hallucination Risk from Internal Signals in LLM Question Answering
• A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detection

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