Summary of Uncertainty Of Thoughts: Uncertainty-aware Planning Enhances Information Seeking in Large Language Models, by Zhiyuan Hu et al.
Uncertainty of Thoughts: Uncertainty-Aware Planning Enhances Information Seeking in Large Language Models
by Zhiyuan Hu, Chumin Liu, Xidong Feng, Yilun Zhao, See-Kiong Ng, Anh Tuan Luu, Junxian He, Pang Wei Koh, Bryan Hooi
First submitted to arxiv on: 5 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 The paper introduces Uncertainty of Thoughts (UoT), an algorithm to enable large language models (LLMs) to actively seek information by asking effective questions. UoT combines uncertainty-aware simulation, uncertainty-based rewards, and reward propagation to select optimal questions. This approach leads to significant improvements in task completion rates (38.1% average) and efficiency across medical diagnosis, troubleshooting, and the 20 Questions game. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper helps computers talk better by learning to ask good questions. Right now, computers can only answer questions they’re given, but humans are great at asking follow-up questions to get more information. The UoT algorithm lets computers do this too! It’s like a special tool that makes the computer think about what might happen if it asks different questions and chooses the best one. This helps the computer solve tasks better and faster. |
