arXiv cs.LG
Coupled Calibration and Learning: Mitigating Teacher Bias in LLM Distillation without Target-Domain Reward Feedback
결합 보정과 학습: 목표 도메인 보상 피드백 없이 LLM 증류에서 교사 편향 완화하기
No write-up yet — this entry is still just the auto-fetched hook. Aaron's own summary (200–500 words) will replace this note once he's written it.