Different Facets of Verbalised Overconfidence: an Interpretability Study
Quick summary
arXiv:2608.18106v1 Announce Type: cross Abstract: Large language models tend to overconfidence, giving assertive answers when the evidence suggests hedging or abstention. Using controlled reasoning scenarios that manipulate logical necessity and possibility, we study this behavior in Qwen3-4B, across three ways to express uncertainty: verbal epistemic markers, abstention, and numeric confidence scores. Our results confirm this tendency toward overconfidence, particularly when the model is prompted to output a numeric confidence score. At the interpretability level, we propose a method that dif
Key takeaways
- arXiv:2608.18106v1 Announce Type: cross Abstract: Large language models tend to overconfidence, giving assertive answers when the evidence suggests hedging or abstention.
- Using controlled reasoning scenarios that manipulate logical necessity and possibility, we study this behavior in Qwen3-4B, across three ways to express uncertainty: verbal epistemic markers, abstention, and numeric confidence scores.
- Our results confirm this tendency toward overconfidence, particularly when the model is prompted to output a numeric confidence score.
Why it matters
The value of this work lies as much in how it was tested as in the claim itself. Sample design, baselines, uncertainty and replication help separate a laboratory result from real-world impact.
Member comments