Summary of Reft: Representation Finetuning For Language Models, by Zhengxuan Wu and Aryaman Arora and Zheng Wang and Atticus Geiger and Dan Jurafsky and Christopher D. Manning and Christopher Potts
ReFT: Representation Finetuning for Language Models
by Zhengxuan Wu, Aryaman Arora, Zheng Wang, Atticus Geiger, Dan Jurafsky, Christopher D. Manning, Christopher Potts
First submitted to arxiv on: 4 Apr 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 The paper presents a family of Representation Finetuning (ReFT) methods, which operate on a frozen base model and learn task-specific interventions on hidden representations. The strong instance of the ReFT family is Low-rank Linear Subspace ReFT (LoReFT), which outperforms state-of-the-art parameter-efficient finetuning (PEFT) methods while being 15x–65x more efficient. LoReFT is a drop-in replacement for existing PEFTs and can be used on various tasks such as commonsense reasoning, arithmetic reasoning, instruction-tuning, and GLUE. The paper showcases the effectiveness of LoReFT on these tasks, demonstrating its potential to deliver the best balance of efficiency and performance. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about a new way to make AI models more efficient without losing their ability to understand and do tasks well. Instead of updating all the weights in the model, which can be slow and require a lot of data, this method focuses on changing a few key parts that are important for the task. The result is an AI model that can learn new things quickly and accurately, while using fewer resources than before. |
Keywords
* Artificial intelligence * Instruction tuning * Parameter efficient
