LifeAlign: Lifelong Alignment for Large Language Models with Memory-Augmented Focalized Preference Optimization

Documenti analoghi

• Black-box Model Merging for Language-Model-as-a-Service with Massive Model Repositories
  di: Chen, Shilian, et al.
  Pubblicazione: (2025)
• Forget What's Sensitive, Remember What Matters: Token-Level Differential Privacy in Memory Sculpting for Continual Learning
  di: Zhan, Bihao, et al.
  Pubblicazione: (2025)
• AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution
  di: Yang, Yutao, et al.
  Pubblicazione: (2026)
• Reinforced Interactive Continual Learning via Real-time Noisy Human Feedback
  di: Yang, Yutao, et al.
  Pubblicazione: (2025)
• Teaching LLMs for Step-Level Automatic Math Correction via Reinforcement Learning
  di: Li, Junsong, et al.
  Pubblicazione: (2025)