paper-with-me

Papers

Leveraging Unstructured Text Data for Federated Instruction Tuning of Large Language Models

2024-09-11 · Rui Ye, Rui Ge, Yuchi Fengting, Jingyi Chai, Yanfeng Wang, Siheng Chen

Federated instruction tuning enables multiple clients to collaboratively fine-tune a shared large language model (LLM) that can follow humans' instructions without directly sharing raw data. However, existing literature impractically requires that all the clients readily hold instruction-tuning data (i.e., structured instruction-response pairs), which necessitates massive human annotations since clients' data is usually unstructured text instead. Addressing this, we propose a novel and flexible framework FedIT-U2S, which can automatically transform unstructured corpus into structured data for federated instruction tuning. FedIT-U2S consists two key steps: (1) few-shot instruction-tuning data generation, where each unstructured data piece together with several examples is combined to prompt an LLM in generating an instruction-response pair. To further enhance the flexibility, a retrieval-based example selection technique is proposed, where the examples are automatically selected based on the relatedness between the client's data piece and example pool, bypassing the need of determining examples in advance. (2) A typical federated instruction tuning process based on the generated data. Overall, FedIT-U2S can be applied to diverse scenarios as long as the client holds valuable text corpus, broadening the application scope of federated instruction tuning. We conduct a series of experiments on three domains (medicine, knowledge, and math), showing that our proposed FedIT-U2S can consistently and significantly brings improvement over the base LLM.

📄 PDF Abstract BibTeX arXiv:2409.07136

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModellingLarge Language ModelMath

Methods 이 논문이 사용한 방법론

BASE 설명 없음

Similar Papers 제목 키워드 기반

Enabling Robots to Understand Incomplete Natural Language Instructions Using Commonsense Reasoning

2019-04-29 · Haonan Chen, Hao Tan, Alan Kuntz, Mohit Bansal 외

Enabling robots to understand instructions provided via spoken natural language would facilitate interaction between robots and people in a variety of settings in homes and workplaces. However, natural language instructi…

Common Sense ReasoningLanguage ModelingLanguage Modelling

Data Quality Control in Federated Instruction-tuning of Large Language Models

2024-10-15 · Yaxin Du, Rui Ye, Fengting Yuchi, Wanru Zhao 외

By leveraging massively distributed data, federated learning (FL) enables collaborative instruction tuning of large language models (LLMs) in a privacy-preserving way. While FL effectively expands the data quantity, the …

Federated LearningPrivacy Preserving

Towards Building the Federated GPT: Federated Instruction Tuning

2023-05-09 · Jianyi Zhang, Saeed Vahidian, Martin Kuo, Chunyuan Li 외

While "instruction-tuned" generative large language models (LLMs) have demonstrated an impressive ability to generalize to new tasks, the training phases heavily rely on large amounts of diverse and high-quality instruct…

Federated Learning

FineInstructions: Scaling Synthetic Instructions to Pre-Training Scale

2026-01-29 · Ajay Patel, Colin Raffel, Chris Callison-Burch arxiv

Due to limited supervised training data, large language models (LLMs) are typically pre-trained via a self-supervised "predict the next word" objective on a vast amount of unstructured text data. To make the resulting mo…

FewFedPIT: Towards Privacy-preserving and Few-shot Federated Instruction Tuning

2024-03-10 · Zhuo Zhang, Jingyuan Zhang, Jintao Huang, Lizhen Qu 외

Instruction tuning has been identified as a crucial technique for optimizing the performance of large language models (LLMs) in generating human-aligned responses. Nonetheless, gathering diversified and superior-quality …

Federated LearningFew-Shot LearningIn-Context LearningPrivacy Preserving+1