Summary of Promptkd: Distilling Student-friendly Knowledge For Generative Language Models Via Prompt Tuning, by Gyeongman Kim et al.
PromptKD: Distilling Student-Friendly Knowledge for Generative Language Models via Prompt Tuning
by Gyeongman Kim, Doohyuk Jang, Eunho Yang
First submitted to arxiv on: 20 Feb 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 Recent advancements in large language models (LLMs) have raised concerns about inference costs, emphasizing the need for research into model compression. This paper explores a new approach called PromptKD, which utilizes prompt tuning to enable generative LLMs to transfer student-friendly knowledge. Unlike previous works, PromptKD achieves state-of-the-art performance while adding only 0.0007% of the teacher’s parameters as prompts. Extensive experiments on instruction-following datasets demonstrate the effectiveness of distilling student-friendly knowledge in alleviating exposure bias and leading to performance enhancements. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper looks at ways to make big language models smaller so they use less computer power. One way is called PromptKD, which helps these models learn from other, simpler models. It’s like helping a big student learn from a smaller one. The researchers tested this method on some special kinds of data and found that it worked really well. They also showed that using this method makes the language models better at following instructions. |
Keywords
* Artificial intelligence * Inference * Model compression * Prompt
