KaFT: Knowledge-aware Fine-tuning for Boosting LLMs' Domain-specific Question-Answering Performance

Documenti analoghi

• Resolving Knowledge Conflicts in Domain-specific Data Selection: A Case Study on Medical Instruction-tuning
  di: Zhong, Qihuang, et al.
  Pubblicazione: (2025)
• Try, Check and Retry: A Divide-and-Conquer Framework for Boosting Long-context Tool-Calling Performance of LLMs
  di: Chen, Kunfeng, et al.
  Pubblicazione: (2026)
• ROSE Doesn't Do That: Boosting the Safety of Instruction-Tuned Large Language Models with Reverse Prompt Contrastive Decoding
  di: Zhong, Qihuang, et al.
  Pubblicazione: (2024)
• PANDA: Prompt Transfer Meets Knowledge Distillation for Efficient Model Adaptation
  di: Zhong, Qihuang, et al.
  Pubblicazione: (2022)
• Revisiting Knowledge Distillation for Autoregressive Language Models
  di: Zhong, Qihuang, et al.
  Pubblicazione: (2024)