V-SEAM: Visual Semantic Editing and Attention Modulating for Causal Interpretability of Vision-Language Models

Documenti analoghi

• From Heads to Neurons: Causal Attribution and Steering in Multi-Task Vision-Language Models
  di: Wang, Qidong, et al.
  Pubblicazione: (2026)
• SEAM: A Stochastic Benchmark for Multi-Document Tasks
  di: Lior, Gili, et al.
  Pubblicazione: (2024)
• SEAM: Semantically Equivalent Across Modalities Benchmark for Vision-Language Models
  di: Tang, Zhenwei, et al.
  Pubblicazione: (2025)
• Large Language Models Are Active Critics in NLG Evaluation
  di: Xu, Shuying, et al.
  Pubblicazione: (2024)
• Enhancing Semantic Consistency of Large Language Models through Model Editing: An Interpretability-Oriented Approach
  di: Yang, Jingyuan, et al.
  Pubblicazione: (2025)