RATE: Causal Explainability of Reward Models with Imperfect Counterfactuals

Documenti analoghi

• The Information Geometry of Softmax: Probing and Steering
  di: Park, Kiho, et al.
  Pubblicazione: (2026)
• Why is constrained neural language generation particularly challenging?
  di: Garbacea, Cristina, et al.
  Pubblicazione: (2022)
• BoNBoN Alignment for Large Language Models and the Sweetness of Best-of-n Sampling
  di: Gui, Lin, et al.
  Pubblicazione: (2024)
• Incorporating Hierarchical Semantics in Sparse Autoencoder Architectures
  di: Muchane, Mark, et al.
  Pubblicazione: (2025)
• Personalized Benchmarking: Evaluating LLMs by Individual Preferences
  di: Garbacea, Cristina, et al.
  Pubblicazione: (2026)