AttributionLab: Faithfulness of Feature Attribution Under Controllable Environments

Documenti analoghi

• A Dual-Perspective Approach to Evaluating Feature Attribution Methods
  di: Li, Yawei, et al.
  Pubblicazione: (2023)
• Calibrating LLMs with Information-Theoretic Evidential Deep Learning
  di: Li, Yawei, et al.
  Pubblicazione: (2025)
• FinerCut: Finer-grained Interpretable Layer Pruning for Large Language Models
  di: Zhang, Yang, et al.
  Pubblicazione: (2024)
• On Discprecncies between Perturbation Evaluations of Graph Neural Network Attributions
  di: Rezaei, Razieh, et al.
  Pubblicazione: (2024)
• RelP: Faithful and Efficient Circuit Discovery in Language Models via Relevance Patching
  di: Jafari, Farnoush Rezaei, et al.
  Pubblicazione: (2025)