Instruction tuning with loss over instructions
Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning
RETAINING BY DOING: THE ROLE OF ON-POLICY DATA IN MITIGATING FORGETTING
Proximal Gradient and Subgradients
Different Designs For LLM KD Loss(II)
Importance-Aware Data Selection for Efficient LLM Instruction Tuning
Scaling Up Dataset Distillation to ImageNet-1K with Constant Memory
Squeeze, Recover and Relabel: Dataset Condensation at ImageNet Scale From A New Perspective
Training-Inference Mismatch In LLM KD(II)
FROM CORRECTION TO MASTERY: REINFORCED DISTILLATION OF LARGE LANGUAGE MODEL AGENTS