@inproceedings{messmer-etal-2025-enhancing,
title = "Enhancing Multilingual {LLM} Pretraining with Model-Based Data Selection",
author = "Messmer, Bettina and
Sabol{\v{c}}ec, Vinko and
Jaggi, Martin",
editor = {Gerber, Jonathan and
Cieliebak, Mark and
Tuggener, Don and
H{\"u}rlimann, Manuela},
booktitle = "Proceedings of the 10th edition of the Swiss Text Analytics Conference",
month = may,
year = "2025",
address = "Winterthur, Switzerland",
publisher = "Association for Computational Linguistics",
url = "https://preview.aclanthology.org/old-master/2025.swisstext-1.4/",
pages = "31--56"
}Markdown (Informal)
[Enhancing Multilingual LLM Pretraining with Model-Based Data Selection](https://preview.aclanthology.org/old-master/2025.swisstext-1.4/) (Messmer et al., SwissText 2025)
ACL