Thinking Mode Induces Confidence Compression in Reasoning LLMs: A Pre-Registered Type-2 SDT Analysis

Reasoning LLMs generate explicit thinking traces before answering, improving accuracy on knowledge-intensive tasks. We tested whether thinking mode also improves the discriminative power of token-probability-derived confidence signals. In a pre-registered study (OSF: osf.io/2jwub), three 7-8B reasoning models answered 2,000 TriviaQA items in thinking and non-thinking mode. Thinking mode improved accuracy but significantly reduced NLP-based AUROC2 in all three models (Qwen3-8B: delta = -0.231, 95% CI [-0.262, -0.198]). The mechanism is NLP compression: thinking-mode NLP variance dropped to 16% of non-thinking levels. Stage 1 of 2 in a pre-registered design.