When No Benchmark Exists: Validating Comparative LLM Safety Scoring Without Ground-Truth Labels

Documenti analoghi

• HEDGE: Hallucination Estimation via Dense Geometric Entropy for VQA with Vision-Language Models
  di: Gautam, Sushant, et al.
  Pubblicazione: (2025)
• Point, Detect, Count: Multi-Task Medical Image Understanding with Instruction-Tuned Vision-Language Models
  di: Gautam, Sushant, et al.
  Pubblicazione: (2025)
• SoccerChat: Integrating Multimodal Data for Enhanced Soccer Game Understanding
  di: Gautam, Sushant, et al.
  Pubblicazione: (2025)
• Superior Scoring Rules for Probabilistic Evaluation of Single-Label Multi-Class Classification Tasks
  di: Ahmadian, Rouhollah, et al.
  Pubblicazione: (2024)
• VideoHEDGE: Entropy-Based Hallucination Detection for Video-VLMs via Semantic Clustering and Spatiotemporal Perturbations
  di: Gautam, Sushant, et al.
  Pubblicazione: (2026)