Summary of Opentab: Advancing Large Language Models As Open-domain Table Reasoners, by Kezhi Kong et al.
OpenTab: Advancing Large Language Models as Open-domain Table Reasoners
by Kezhi Kong, Jiani Zhang, Zhengyuan Shen, Balasubramaniam Srinivasan, Chuan Lei, Christos Faloutsos, Huzefa Rangwala, George Karypis
First submitted to arxiv on: 22 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- 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 paper proposes a new framework called OpenTab, which enables Large Language Models (LLMs) to reason about structured table data. This is achieved by leveraging a retriever that fetches relevant tables and then generates SQL programs to parse the retrieved tables efficiently. The framework utilizes intermediate data derived from the SQL executions to conduct grounded inference and produce accurate responses. Experimental results show that OpenTab outperforms baselines in both open- and closed-domain settings, achieving up to 21.5% higher accuracy. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary OpenTab is a new way for computers to understand table data, like spreadsheets or databases. It uses special language models called Large Language Models (LLMs) to find important information in tables and then use that info to answer questions. This helps computers do tasks with tables that they couldn’t do before. The paper shows that OpenTab works better than other methods in many cases. |
Keywords
* Artificial intelligence * Inference
