20.500.12556/RUL-166792 Train your cake and eat it too! Repurposing collaborative training to tailor LLMs to private data without sharing In the emerging field of large language models (LLMs), a significant challenge arises when organizations with vast datasets lack the computational resources to independently train and fine-tune models. This issue stems from privacy, compliance, and resource constraints: organizations cannot share their sensitive data but still need external computational assistance for model training. In this paper, we implement, enhance, and empirically compare several methods, including Split Learning (SL) and select Federated Learning (FL) methods, which enable data-rich yet compute-poor clients to offload LLM training without sharing raw data. Our study evaluates these methods across multiple dimensions, including model quality and training time. energy usage digital data poraba energije digitalni podatki true false true Angleški jezik Slovenski jezik Licenca Creative Commons je navedena na pristajalni strani članka (glej izvorni URL): "Licensed under Crative Commons Atribution 4.0 International". (Datum opombe 24. 1. 2025) Drugo 2025-01-24 14:17:40 2025-01-24 14:17:41 2025-01-25 04:13:10 0000-00-00 00:00:00 2024 0 0 Str. 1-10 0000-00-00 Zaloznikova Objavljeno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 004 221660675 221659651 RAZ_Radovic_Boris_2024.pdf RAZ_Radovic_Boris_2024.pdf 1 E45BC051716C6DCC50601F8294586511 a24439ba4ff9bb09bcb8c879678f004980459b027f4c876898959453e54d3363 695e8e8c-da56-11ef-b232-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=198709 https://openreview.net/forum?id=FGupKd365r 1 cb6f6b62-da54-11ef-b232-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=198704 Fakulteta za računalništvo in informatiko 0 0 0