Dialogue Action Tokens: Steering Language Models in Goal-Directed Dialogue with a Multi-Turn Planner

Documenti analoghi

• When Bad Data Leads to Good Models
  di: Li, Kenneth, et al.
  Pubblicazione: (2025)
• Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
  di: Li, Kenneth, et al.
  Pubblicazione: (2023)
• Measuring and Controlling Instruction (In)Stability in Language Model Dialogs
  di: Li, Kenneth, et al.
  Pubblicazione: (2024)
• Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task
  di: Li, Kenneth, et al.
  Pubblicazione: (2022)
• What Does it Mean for a Neural Network to Learn a "World Model"?
  di: Li, Kenneth, et al.
  Pubblicazione: (2025)