Summary of Gear: Graph-enhanced Agent For Retrieval-augmented Generation, by Zhili Shen et al.
GeAR: Graph-enhanced Agent for Retrieval-augmented Generation
by Zhili Shen, Chenxin Diao, Pavlos Vougiouklis, Pascual Merita, Shriram Piramanayagam, Damien Graux, Dandan Tu, Zeren Jiang, Ruofei Lai, Yang Ren, Jeff Z. Pan
First submitted to arxiv on: 24 Dec 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 This paper introduces GeAR, a retrieval-augmented generation system that improves performance in multi-hop question answering scenarios. The authors propose two key innovations: graph expansion, which enhances conventional retrievers like BM25, and an agent framework that incorporates graph expansion. Evaluation on three datasets demonstrates GeAR’s superior retrieval performance, with state-of-the-art results on the challenging MuSiQue dataset, requiring fewer tokens and iterations compared to other multi-step retrieval systems. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper creates a new way for computers to search for answers in complicated question-answering tasks. The system, called GeAR, gets better results than before by expanding how it looks at information and using a special framework. It tests this system on three different datasets and shows that it does much better than other systems, especially on one dataset that’s really hard. |
Keywords
» Artificial intelligence » Question answering » Retrieval augmented generation
