CrossLM: A Data-Free Collaborative Fine-Tuning Framework for Large and Small Language Models
Open Access
- 23 June 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 124-137
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (62402267, 62341201)
This publication has 13 references indexed in Scilit:
- On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey2024
- Self-Instruct: Aligning Language Models with Self-Generated Instructions2023
- TailorFL2022
- FedBERT: When Federated Learning Meets Pre-trainingACM Transactions on Intelligent Systems and Technology, 2022
- BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models2022
- Hermes2021
- Towards Efficient Scheduling of Federated Mobile Devices Under Computational and Statistical HeterogeneityIEEE Transactions on Parallel and Distributed Systems, 2021
- The Power of Scale for Parameter-Efficient Prompt Tuning2021
- Don’t Stop Pretraining: Adapt Language Models to Domains and Tasks2020
- Neural Network Acceptability JudgmentsTransactions of the Association for Computational Linguistics, 2019