Summary of Generative Retrieval with Large Language Models, by Ye Wang et al.
Generative Retrieval with Large Language Models
by Ye Wang, Xinrun Xu, Rui Xie, Wenxin Hu, Wei Ye
First submitted to arxiv on: 26 Feb 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
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 proposes a two-stage framework for large language models (LLMs) to recall reference passages from any starting position. The first stage prompts the LLM to retrieve document title identifiers, which is used to obtain a coarse-grained document set. In the second stage, the LLM uses constrained decoding to locate a short prefix within the stored documents and then retrieves the complete passage. Experimental results on KILT knowledge-sensitive tasks demonstrate that LLMs can effectively recall reference passages, leading to improved performance in downstream tasks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps computers remember where they found important information from books or articles. Instead of asking for help, the computer uses a special type of AI model called a large language model (LLM) to find the right passage on its own. The LLM looks at document titles first and then finds the exact sentence it needs. This makes it easier for computers to complete tasks that require remembering specific information. |
Keywords
» Artificial intelligence » Large language model » Recall
