SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignment

Documenti analoghi

• SPARD: Self-Paced Curriculum for RL Alignment via Integrating Reward Dynamics and Data Utility
  di: Zhi, Xuyang, et al.
  Pubblicazione: (2026)
• RAG-IGBench: Innovative Evaluation for RAG-based Interleaved Generation in Open-domain Question Answering
  di: Zhang, Rongyang, et al.
  Pubblicazione: (2025)
• Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal
  di: Huang, Jianheng, et al.
  Pubblicazione: (2024)
• MEGA: Second-Order Gradient Alignment for Catastrophic Forgetting Mitigation in GFSCIL
  di: Pang, Jinhui, et al.
  Pubblicazione: (2025)
• Mitigating Catastrophic Forgetting in Large Language Models with Forgetting-aware Pruning
  di: Huang, Wei, et al.
  Pubblicazione: (2025)