Addressing task conflicts in LLMs multi-task fine-tuning with task-specific subnetwork refinement

DOI10.1007/S10994-025-06885-ZMaRDI QIDQ6890066zbMATH OpenFDO

Authors Yiqun Wang, Chaoqun Wan, Xiang Tian, Xuesong Liu, Yao-Wu Chen

Publication date 4 December 2025

Published in Machine Learning (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/S10994-025-06885-Z

zbMATH Keywords

model interpretabilitylarge language modelinstruction fine-tuningmulti-task training

Mathematics Subject Classification ID

Logic in artificial intelligence (68T27)

This page was built for publication: Addressing task conflicts in LLMs multi-task fine-tuning with task-specific subnetwork refinement

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6890066)