{"ID":2896944,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.08843","arxiv_id":"2507.08843","title":"Can We Predict Your Next Move Without Breaking Your Privacy?","abstract":"We propose FLLL3M--Federated Learning with Large Language Models for Mobility Modeling--a privacy-preserving framework for Next-Location Prediction (NxLP). By retaining user data locally and leveraging LLMs through an efficient outer product mechanism, FLLL3M ensures high accuracy with low resource demands. It achieves SOT results on Gowalla (Acc@1: 12.55, MRR: 0.1422), WeePlace (10.71, 0.1285), Brightkite (10.42, 0.1169), and FourSquare (8.71, 0.1023), while reducing parameters by up to 45.6% and memory usage by 52.7%.","short_abstract":"We propose FLLL3M--Federated Learning with Large Language Models for Mobility Modeling--a privacy-preserving framework for Next-Location Prediction (NxLP). By retaining user data locally and leveraging LLMs through an efficient outer product mechanism, FLLL3M ensures high accuracy with low resource demands. It achieves...","url_abs":"https://arxiv.org/abs/2507.08843","url_pdf":"https://arxiv.org/pdf/2507.08843v1","authors":"[\"Arpita Soni\",\"Sahil Tripathi\",\"Gautam Siddharth Kashyap\",\"Manaswi Kulahara\",\"Mohammad Anas Azeez\",\"Zohaib Hasan Siddiqui\",\"Nipun Joshi\",\"Jiechao Gao\"]","published":"2025-07-08T08:13:34Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}