SPEX: Scaling Feature Interaction Explanations for LLMs

Documenti analoghi

• ProxySPEX: Inference-Efficient Interpretability via Sparse Feature Interactions in LLMs
  di: Butler, Landon, et al.
  Pubblicazione: (2025)
• Learning to Understand: Identifying Interactions via the Möbius Transform
  di: Kang, Justin S., et al.
  Pubblicazione: (2024)
• The Fair Value of Data Under Heterogeneous Privacy Constraints in Federated Learning
  di: Kang, Justin, et al.
  Pubblicazione: (2023)
• Online Assortment and Price Optimization Under Contextual Choice Models
  di: Erginbas, Yigit Efe, et al.
  Pubblicazione: (2025)
• Adaptive Sparse Möbius Transforms for Learning Polynomials
  di: Erginbas, Yigit Efe, et al.
  Pubblicazione: (2026)