Source Prompt: Coordinated Pre-training of Language Models on Diverse Corpora from Multiple Sources.

@inproceedings{xu-2024-source, author = {Yipei Xu and Dakuan Lu and Jiaqing Liang and Jin Zhao and Xintao Wang and Hengkui Wu and Ken Chen and Liujiang Liu and Yingsi Xin and Xuepeng Liu and Yanghua Xiao and Zhixu Li}, editor = {Edoardo Serra and Francesca Spezzano}, title = {{Source Prompt: Coordinated Pre-training of Language Models on Diverse Corpora from Multiple Sources}}, booktitle = {{Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, CIKM 2024, Boise, ID, USA, October 21-25, 2024}}, pages = {2732--2741}, publisher = {ACM}, year = {2024}, url = {https://doi.org/10.1145/3627673.3679835}, doi = {https://doi.org/10.1145/3627673.3679835} }