Summary of Kasa: Knowledge-aware Singular-value Adaptation Of Large Language Models, by Fan Wang et al.
KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language Models
by Fan Wang, Juyong Jiang, Chansung Park, Sunghun Kim, Jing Tang
First submitted to arxiv on: 8 Dec 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
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 This paper proposes a new approach to fine-tuning large language models (LLMs) for specific tasks or domains, building upon the simplicity and efficiency of LoRA. The issue with existing parameter-efficient fine-tuning (PEFT) methods like LoRA is that they disregard noisy or irrelevant knowledge, leading to suboptimal performance. To address this limitation, the authors introduce Knowledge-aware Singular-value Adaptation (KaSA), a PEFT method that leverages singular value decomposition (SVD) to dynamically activate knowledge based on its relevance to the task at hand. KaSA outperforms 14 popular PEFT baselines across 16 benchmarks and 4 synthetic datasets, demonstrating its efficacy and adaptability. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about making large language models work better for specific tasks. Right now, it takes a lot of computer power and memory to make these models do what we want them to do. To fix this problem, the authors created a new way to fine-tune the models that only uses important information. This new method, called KaSA, does a great job of making sure the model only uses knowledge that is relevant to the task it’s doing. The authors tested their method on many different tasks and datasets, and it worked better than other methods in almost every case. |
Keywords
» Artificial intelligence » Fine tuning » Lora » Parameter efficient
