Revisiting Knowledge Distillation for Autoregressive Language Models

Qihuang Zhong, Liang Ding, Li Shen, Juhua Liu, Bo Du, Dacheng Tao


Abstract
Knowledge distillation (KD) is a common approach to compress a teacher model to reduce its inference cost and memory footprint, by training a smaller student model. However, in the context of autoregressive language models (LMs), we empirically find that larger teacher LMs might dramatically result in a poorer student. In response to this problem, we conduct a series of analyses and reveal that different tokens have different teaching modes, neglecting which will lead to performance degradation. Motivated by this, we propose a simple yet effective adaptive teaching approach (ATKD) to improve the KD. The core of ATKD is to reduce rote learning and make teaching more diverse and flexible. Extensive experiments on 8 LM tasks show that, with the help of ATKD, various baseline KD methods can achieve consistent and significant performance gains (up to +3.04% average score) across all model types and sizes. More encouragingly, ATKD can improve the student model generalization effectively.
Anthology ID:
2024.acl-long.587
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
10900–10913
Language:
URL:
https://aclanthology.org/2024.acl-long.587
DOI:
10.18653/v1/2024.acl-long.587
Bibkey:
Cite (ACL):
Qihuang Zhong, Liang Ding, Li Shen, Juhua Liu, Bo Du, and Dacheng Tao. 2024. Revisiting Knowledge Distillation for Autoregressive Language Models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 10900–10913, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Revisiting Knowledge Distillation for Autoregressive Language Models (Zhong et al., ACL 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/autopr/2024.acl-long.587.pdf