Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs

arXiv:2604.01457v3 Announce Type: replace Abstract: Large language models are often not just wrong, but confidently wrong: when they produce factually incorrect answers, they tend to verbalize overly high confidence rather than signal uncertainty. Such verbalized overconfidence can mislead users and weaken confidence scores as a reliable uncertainty signal, yet its internal mechanisms remain poorly understood. We present a circuit-level mechanistic analysis of this inflated verbalized confidence in LLMs, organized around three axes: capturing verbalized confidence as a differentiable internal signal, identifying the circuits that causally inflate it, and leveraging these insights for targeted inference-time recalibration. Across two instruction-tuned LLMs on three datasets, we find that a compact set of MLP blocks and attention heads, concentrated in middle-to-late layers, consistently writes the confidence-inflation signal at the final token position. We further show that targeted inference-time interventions on these circuits substantially improve calibration. Together, our results suggest that verbalized overconfidence in LLMs is driven by identifiable internal circuits and can be mitigated through targeted intervention.

Related

• ADVICE: Answer-Dependent Verbalized Confidence Estimation
• ORCE: Order-Aware Alignment of Verbalized Confidence in Large Language Models
• CGES: Confidence-Guided Early Stopping for Efficient and Accurate Self-Consistency
• Metacognitive Behavioral Tuning of Large Language Models for Multi-Hop Question Answering

Source: arXiv cs.CL | 2026-07-28