Self-Verified Distillation: Your Language Model Is Secretly Its Own Synthetic Data Pipeline

Documenti analoghi

• Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States
  di: Choi, Yunho, et al.
  Pubblicazione: (2026)
• Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data
  di: Ou, Jingyang, et al.
  Pubblicazione: (2024)
• To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Models
  di: Barbulescu, George-Octavian, et al.
  Pubblicazione: (2024)
• Distilled Self-Critique of LLMs with Synthetic Data: a Bayesian Perspective
  di: Gallego, Victor
  Pubblicazione: (2023)
• Explain in Your Own Words: Improving Reasoning via Token-Selective Dual Knowledge Distillation
  di: Kim, Minsang, et al.
  Pubblicazione: (2026)