The Geometry of Self-Verification in a Task-Specific Reasoning Model

Documenti analoghi

• Relational Composition in Neural Networks: A Survey and Call to Action
  di: Wattenberg, Martin, et al.
  Pubblicazione: (2024)
• Dialogue Action Tokens: Steering Language Models in Goal-Directed Dialogue with a Multi-Turn Planner
  di: Li, Kenneth, et al.
  Pubblicazione: (2024)
• When Bad Data Leads to Good Models
  di: Li, Kenneth, et al.
  Pubblicazione: (2025)
• Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task
  di: Li, Kenneth, et al.
  Pubblicazione: (2022)
• Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
  di: Li, Kenneth, et al.
  Pubblicazione: (2023)