Summary of Federated Data-efficient Instruction Tuning For Large Language Models, by Zhen Qin et al.
Federated Data-Efficient Instruction Tuning for Large Language Models
by Zhen Qin, Zhaomin Wu, Bingsheng He, Shuiguang Deng
First submitted to arxiv on: 14 Oct 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed approach, Federated Data-Efficient Instruction Tuning (FedHDS), aims to improve the performance of pre-trained large language models (LLMs) by reducing the data required for fine-tuning while maintaining responsiveness to human instructions. FedHDS utilizes a representative subset of edge-side data, referred to as a coreset, to tune the LLM. The approach reduces data redundancy at both intra-client and inter-client levels through a hierarchical data selection framework, which jointly selects a small number of representative data samples for local training without sharing raw data. Experimental results across six scenarios demonstrate that FedHDS significantly reduces the amount of data required for fine-tuning while improving responsiveness to unseen tasks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary FedHDS is a new way to improve pre-trained language models by using less data. This approach helps make language models more responsive to human instructions, which is important for tasks like chatbots and virtual assistants. The method uses a special subset of data from each device, called a coreset, to fine-tune the model without sharing all the raw data. This reduces the amount of data needed and makes it faster and more efficient. |
Keywords
» Artificial intelligence » Fine tuning » Instruction tuning
