Lightweight Cross-Lingual Federated Prompt Tuning for Low-Resource Languages
Azam, Ubaid Razzak, Imran Jameel, Shoaib
Azam, Ubaid
Razzak, Imran
Jameel, Shoaib
Supervisor
Department
Computational Biology
Embargo End Date
Type
Conference proceeding
Date
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Multilingual NLP faces challenges of data heterogeneity, privacy, and limited computational resources, especially for low-resource languages. Centralised methods risk privacy breaches, while federated learning struggles with communication overhead and poor cross-lingual generalisation. We propose FLiP (Federated Lightweight Prompt-tuning), a privacy-preserving, resource-efficient, generalizable framework integrating prompt-based learning with federated optimisation. FLiP eliminates communication overhead, reduces trainable parameters to 16%, and cuts GPU memory use by 90%. Experiments show superior generalisation and efficiency under both IID and Non-IID settings, establishing FLiP as a scalable, privacy-aware solution for multilingual NLP, particularly in low-resource and indigenous language contexts.
Citation
U. Azam, I. Razzak, S. Jameel, "Lightweight Cross-Lingual Federated Prompt Tuning for Low-Resource Languages," 2026, pp. 3304-3316.
Source
Proceedings of the Fifteenth Language Resources and Evaluation Conference (LREC 2026)
Conference
Fifteenth Language Resources and Evaluation Conference (LREC 2026)
Keywords
Subjects
Source
Fifteenth Language Resources and Evaluation Conference (LREC 2026)
Publisher
ELDA (Evaluations and Language resources Distribution Agency)