Summary of Plan-on-graph: Self-correcting Adaptive Planning Of Large Language Model on Knowledge Graphs, by Liyi Chen et al.
Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphs
by Liyi Chen, Panrong Tong, Zhongming Jin, Ying Sun, Jieping Ye, Hui Xiong
First submitted to arxiv on: 31 Oct 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: None
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 Plan-on-Graph (PoG) paradigm enables large language models (LLMs) to adaptively explore reasoning paths in knowledge graphs (KGs), alleviating limitations in existing KG-augmented LLM approaches. By decomposing questions into sub-objectives, PoG iteratively updates memory and reflects on the need for self-correction, ensuring efficient and effective graph reasoning. This novel approach combines Guidance, Memory, and Reflection mechanisms to guarantee adaptive breadth of planning. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A new way to help big language models learn from knowledge graphs is proposed. This method, called Plan-on-Graph (PoG), lets models explore different paths in the graph and correct any mistakes they make along the way. PoG works by breaking down complex questions into smaller parts, then repeatedly exploring the graph, updating what it knows, and reflecting on its progress until it finds the right answer. |
