Lille Neurosciences & Cognition

Token Probabilities to Mitigate Large Language Models Overconfidence in Answering Medical Questions: Quantitative Study

Raphaël Bentegeac, Bastien Le Guellec, Grégory Kuchcinski et al.

2025 · 4 Zit.

Unveiling Inner Doubts beyond ChatGPT’s Apparent Overconfidence

Aghilès Hamroun, Philippe Amouyel, Raphaël Bentegeac et al.

2025 · 1 Zit.

Imputation Benchmarking in Clinical Databases: Constraint Enforcement for Bounded Neuropsychological Assessments

Moad Hani, Saïd Mahmoudi, Mohammed BENJELLOUN et al.

2026 · 0 Zit.