REAL: Reading Out Transformer Activations for Precise Localization in Language Model Steering

Documenti analoghi

• VI-OOD: A Unified Representation Learning Framework for Textual Out-of-distribution Detection
  di: Zhan, Li-Ming, et al.
  Pubblicazione: (2024)
• Diversity-grounded Channel Prototypical Learning for Out-of-Distribution Intent Detection
  di: Liu, Bo, et al.
  Pubblicazione: (2024)
• GeoEdit: Geometric Knowledge Editing for Large Language Models
  di: Feng, Yujie, et al.
  Pubblicazione: (2025)
• How Good Are LLMs at Out-of-Distribution Detection?
  di: Liu, Bo, et al.
  Pubblicazione: (2023)
• A Comparative Analysis of Sparse Autoencoder and Activation Difference in Language Model Steering
  di: Xie, Jiaqing
  Pubblicazione: (2025)