Delta Knowledge Distillation for Large Language Models
This work addresses a bottleneck in compressing large language models for deployment, though it is incremental as it builds on existing token-level knowledge distillation methods.
The paper tackles the problem of knowledge distillation for large language models by proposing Delta-KD, which addresses the assumption that student and teacher share the same optimal representation space, and results show substantial improvements in student performance on ROUGE metrics.
Knowledge distillation (KD) is a widely adopted approach for compressing large neural networks by transferring knowledge from a large teacher model to a smaller student model. In the context of large language models, token level KD, typically minimizing the KL divergence between student output distribution and teacher output distribution, has shown strong empirical performance. However, prior work assumes student output distribution and teacher output distribution share the same optimal representation space, a premise that may not hold in many cases. To solve this problem, we propose Delta Knowledge Distillation (Delta-KD), a novel extension of token level KD that encourages the student to approximate an optimal representation space by explicitly preserving the distributional shift Delta introduced during the teacher's supervised finetuning (SFT). Empirical results on ROUGE metrics demonstrate that Delta KD substantially improves student performance while preserving more of the teacher's knowledge.