Summary of Parameter Efficient Reinforcement Learning From Human Feedback, by Hakim Sidahmed and Samrat Phatale and Alex Hutcheson and Zhuonan Lin and Zhang Chen and Zac Yu and Jarvis Jin and Simral Chaudhary and Roman Komarytsia and Christiane Ahlheim and Yonghao Zhu and Bowen Li and Saravanan Ganesh and Bill Byrne and Jessica Hoffmann and Hassan Mansoor and Wei Li and Abhinav Rastogi and Lucas Dixon
Parameter Efficient Reinforcement Learning from Human Feedback
by Hakim Sidahmed, Samrat Phatale, Alex Hutcheson, Zhuonan Lin, Zhang Chen, Zac Yu, Jarvis Jin, Simral Chaudhary, Roman Komarytsia, Christiane Ahlheim, Yonghao Zhu, Bowen Li, Saravanan Ganesh, Bill Byrne, Jessica Hoffmann, Hassan Mansoor, Wei Li, Abhinav Rastogi, Lucas Dixon
First submitted to arxiv on: 15 Mar 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 The proposed Parameter Efficient Reinforcement Learning from Human Feedback (PE-RLHF) setup leverages LoRA fine-tuning for Reward Modeling and Reinforcement Learning to alleviate the computational burden of RLHF. The PE-RLHF setup is empirically evaluated on six diverse datasets, comparing its effectiveness with RLHF in terms of model performance and training resources required. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Reinforcement learning from human feedback helps large language models align with human preferences, but it can be slow and complex. To make it faster and more efficient, researchers have developed a new approach called Parameter Efficient Reinforcement Learning from Human Feedback (PE-RLHF). This approach uses LoRA fine-tuning to reduce the computational burden of RLHF. The PE-RLHF setup is tested on six different datasets and found to be comparable in performance to traditional RLHF, but with significant reductions in training time and memory usage. |
Keywords
* Artificial intelligence * Fine tuning * Lora * Parameter efficient * Reinforcement learning * Reinforcement learning from human feedback * Rlhf
