Reasoning Concentrates Errors, and Self-Consistency Never Notices

arXiv:2609.32035 · cs.AI · Submitted 2026-09-25 · Read on arXiv

cs.AI

Submitted: 2026-09-25

Updated: 2026-09-25

Terminology

• AUROC — 42× in this paper · explained in 2 episodes
• Benchmark — 38× in this paper · explained in 2 episodes
• Accuracy — 31× in this paper · explained in 1 episode
• Consistency — 19× in this paper · explained in 3 episodes
• Self-consistency — 17× in this paper · explained in 2 episodes
• Trace — 13× in this paper · explained in 2 episodes
• Calibration — 8× in this paper · explained in 7 episodes
• Generative AI — 4× in this paper · explained in 2 episodes
• Generalization — 3× in this paper · explained in 13 episodes
• Residualization — 3× in this paper · explained in 2 episodes
• Thinking mode — 3× in this paper · explained in 2 episodes
• Aggregation — 2× in this paper · explained in 1 episode
• Perplexity — 2× in this paper · explained in 3 episodes
• Reasoning Traces — 2× in this paper · explained in 3 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Abstention — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Test-time Scaling — 1× in this paper · explained in 2 episodes
• Twelfth International Conference on Learning Representations — 1× in this paper
• Uncertainty Quantification — 1× in this paper · explained in 8 episodes
• Verifiable Rewards — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• Olmo 3
• When Self-Consistency Backfires: Majority Vote Hurts the Majority of Hard Science Problems for Small LLMs
• Measuring Mathematical Problem Solving With the MATH Dataset
• Gemma 3 Technical Report
• Reported Confidence in LLMs Tracks Commitment More Than Correctness
• BODHI: Do LLMs Branch Out and Discover Heterogeneous Inferences?
• Too Consistent to Detect: A Study of Self-Consistent Errors in LLMs

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection