Med-StepBench: A Hierarchical Reasoning Framework for Evaluating Hallucinations in Medical Vision-Language Models

Documenti analoghi

• Region-Grounded Report Generation for 3D Medical Imaging: A Fine-Grained Dataset and Graph-Enhanced Framework
  di: Nguyen, Cong Huy, et al.
  Pubblicazione: (2026)
• A global potential constrained by the Bohr-Sommerfeld quantization condition for $α$-decay half-lives of even-even nuclei
  di: Huy, Nguyen Gia, et al.
  Pubblicazione: (2026)
• Improved a priori error estimates for a space-time finite element method for parabolic problems
  di: Ta, Thi Thanh Mai, et al.
  Pubblicazione: (2025)
• Beyond the Global Scores: Fine-Grained Token Grounding as a Robust Detector of LVLM Hallucinations
  di: Nguyen, Tuan Dung, et al.
  Pubblicazione: (2026)
• Improving Pareto Set Learning for Expensive Multi-objective Optimization via Stein Variational Hypernetworks
  di: Nguyen, Minh-Duc, et al.
  Pubblicazione: (2024)