Summary of Tree Of Reviews: a Tree-based Dynamic Iterative Retrieval Framework For Multi-hop Question Answering, by Li Jiapeng et al.
Tree of Reviews: A Tree-based Dynamic Iterative Retrieval Framework for Multi-hop Question Answering
by Li Jiapeng, Liu Runze, Li Yabo, Zhou Tong, Li Mingling, Chen Xiang
First submitted to arxiv on: 22 Apr 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Information Retrieval (cs.IR)
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 Multi-hop question answering is a complex problem that requires knowledge-intensive capabilities. Large Language Models (LLMs) use their Chain of Thoughts (CoT) capability to reason step-by-step, but recent methods have introduced retrieval-augmentation in the CoT reasoning to alleviate factual errors caused by outdated and unknown knowledge. However, these chain methods face two problems: irrelevant paragraphs may mislead the reasoning, and an error in the chain structure can lead to a cascade of errors. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Multi-hop question answering is like trying to solve a puzzle with multiple steps. Large Language Models are good at solving puzzles because they can reason step-by-step using their “Chain of Thoughts”. But sometimes, these models make mistakes because they don’t have all the right information. Some researchers tried to fix this by using more information to help the model understand what it doesn’t know. However, this didn’t work perfectly because the model might get confused if it finds irrelevant or wrong information. |
Keywords
» Artificial intelligence » Question answering
