Summary of A Survey on Lora Of Large Language Models, by Yuren Mao et al.
A Survey on LoRA of Large Language Models
by Yuren Mao, Yuhang Ge, Yijiang Fan, Wenyi Xu, Yu Mi, Zhonghao Hu, Yunjun Gao
First submitted to arxiv on: 8 Jul 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 Low-Rank Adaptation (LoRA) is a popular parameter-efficient fine-tuning paradigm that updates dense neural network layers with pluggable low-rank matrices. Its advantages in cross-task generalization and privacy-preserving have made it a topic of interest, with an exponential growth in related literature. This survey provides a comprehensive overview of LoRA’s progress from the perspectives of improving variants, cross-task generalization methods, efficiency-improving methods, data privacy-preserving methods, and applications. The survey also discusses future directions and provides a GitHub page for readers to track updates and initiate discussions. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about Low-Rank Adaptation (LoRA), which helps computers learn from small amounts of data without using too many resources. LoRA has been very successful in recent years, especially when used with other techniques to help computers generalize well across different tasks. The authors are doing a survey on all the progress that’s been made so far and discussing what might be next. |
Keywords
» Artificial intelligence » Fine tuning » Generalization » Lora » Low rank adaptation » Neural network » Parameter efficient
