@inproceedings{khanuja-etal-2021-mergedistill,
title = "{M}erge{D}istill: {M}erging Language Models using Pre-trained Distillation",
author = "Khanuja, Simran and
Johnson, Melvin and
Talukdar, Partha",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://preview.aclanthology.org/Ingest-2025-COMPUTEL/2021.findings-acl.254/",
doi = "10.18653/v1/2021.findings-acl.254",
pages = "2874--2887"
}
Markdown (Informal)
[MergeDistill: Merging Language Models using Pre-trained Distillation](https://preview.aclanthology.org/Ingest-2025-COMPUTEL/2021.findings-acl.254/) (Khanuja et al., Findings 2021)
ACL