mlsanityData to 7 Oct 2026

Federated Data-Efficient Instruction Tuning for Large Language Models

arXiv 2410.10926 ↗First posted 14 Oct 2024cs.LG cs.AI cs.CLcited by 9

Not on the map. Why?

Abstract (arXiv)

Instruction tuning is a crucial step in improving the responsiveness of pretrained large language models (LLMs) to human instructions. Federated learning (FL) helps to exploit the use of vast private instruction data from clients, becoming popular for LLM tuning by improving data diversity. Existing federated tuning simply consumes all local data, causing excessive computational overhead and overfitting to local data, while centralized data-efficient solutions are not suitable for FL due to privacy concerns. This work presents FedHDS, a federated data-efficient instruction tuning approach, which tunes LLMs with a representative subset of edge-side data. It reduces the data redundancy at both intra- and inter-client levels without sharing raw data. Experiments with various LLMs, datasets and partitions show that FedHDS improves Rouge-L on unseen tasks by an average of 10.72% over the SOTA full-data federated instruction tuning methods, while using less than 1.5% of the data samples, improving training efficiency by up to tens of times.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 30 of its 59 references that are in the map. First posted on arXiv 14 Oct 2024.

Builds on

30 of 59 references.

References · 30

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  4. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  5. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  6. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  7. 2023LIMA: Less Is More for Alignmentcited by 1,080
  8. 2022Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Taskscited by 858
  9. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 450
  10. 2023Fine-Tuning Language Models with Just Forward Passescited by 337
  11. 2023From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuningcited by 301
  12. 2023Data-centric Artificial Intelligence: A Surveycited by 202
18 more
  1. 2023Towards Building the Federated GPT: Federated Instruction Tuningcited by 184
  2. 2023FederatedScope-LLM: A Comprehensive Package for Fine-tuning Large Language Models in Federated Learningcited by 146
  3. 2024Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuningcited by 134
  4. 2023#InsTag: Instruction Tagging for Analyzing Supervised Fine-tuning of Large Language Modelscited by 108
  5. 2024Data-efficient Fine-tuning for LLM-based Recommendationcited by 103
  6. 2024Federated Fine-tuning of Large Language Models under Heterogeneous Tasks and Client Resourcescited by 93
  7. 2023SLoRA: Federated Parameter Efficient Fine-Tuning of Language Modelscited by 92
  8. 2024How to Train Data-Efficient LLMscited by 91
  9. 2024A Survey on Data Selection for LLM Instruction Tuningcited by 76
  10. 2024FedBiOT: LLM Local Fine-tuning in Federated Learning without Full Modelcited by 73
  11. 2023Federated Learning of Large Language Models with Parameter-Efficient Prompt Tuning and Adaptive Optimizationcited by 65
  12. 2024Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuningcited by 57
  13. 2023Maybe Only 0.5% Data is Needed: A Preliminary Exploration of Low Training Data Instruction Tuningcited by 56
  14. 2023Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 Kilobytescited by 55
  15. 2023Self-Evolved Diverse Data Sampling for Efficient Instruction Tuningcited by 52
  16. 2023CoachLM: Automatic Instruction Revisions Improve the Data Quality in LLM Instruction Tuningcited by 19
  17. 2013Barnes-Hut-SNEcited by 14
  18. 2024The Synergy between Data and Multi-Modal Large Language Models: A Survey from Co-Development Perspectivecited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 3; 2026: 5.

9 papers.

  1. 2024Personalized Federated Fine-Tuning for LLMs via Data-Driven Heterogeneous Model Architecturescited by 10
  2. 2025Distributed LLMs and Multimodal Large Language Models: A Survey on Advances, Challenges, and Future Directionscited by 10
  3. 2026Decentralized Instruction Tuning: Conflict-Aware Splitting and Weight Mergingcited by 2
  4. 2026Knowing without Acting: The Disentangled Geometry of Safety Mechanisms in Large Language Modelscited by 1
  5. 2026PRISM: Preference-Aware Influence Function Based Data Selection Method for Efficient Fine-Tuningcited by 1
  6. 2025WikiDBGraph: A Data Management Benchmark Suite for Collaborative Learning over Database Siloscited by 0
  7. 2025Federated Fine-Tuning of Sparsely-Activated Large Language Models on Resource-Constrained Devicescited by 0
  8. 2026Federated Prompt Learning: A Unified Framework, Empirical Analysis, and Future Directionscited by 0
  9. 2026Task-Aware Federated Fine-Tuning for MoE-based Large Language Modelscited by 0