Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes

Author:

Arora Simran1,Yang Brandon1,Eyuboglu Sabri1,Narayan Avanika1,Hojel Andrew1,Trummer Immanuel2,Ré Christopher1

Affiliation:

1. Stanford University

2. Cornell University

Abstract

A long standing goal in the data management community is developing systems that input documents and output queryable tables without user effort. Given the sheer variety of potential documents, state-of-the art systems make simplifying assumptions and use domain specific training. In this work, we ask whether we can maintain generality by using the in-context learning abilities of large language models (LLMs). We propose and evaluate Evaporate, a prototype system powered by LLMs. We identify two strategies for implementing this system: prompt the LLM to directly extract values from documents or prompt the LLM to synthesize code that performs the extraction. Our evaluations show a cost-quality tradeoff between these two approaches. Code synthesis is cheap, but far less accurate than directly processing each document with the LLM. To improve quality while maintaining low cost, we propose an extended implementation, Evaporate-Code+, which achieves better quality than direct extraction. Our insight is to generate many candidate functions and ensemble their extractions using weak supervision. Evaporate-Code+ outperforms the state-of-the art systems using a sublinear pass over the documents with the LLM. This equates to a 110X reduction in the number of documents the LLM needs to process across our 16 real-world evaluation settings.

Publisher

Association for Computing Machinery (ACM)

Subject

General Earth and Planetary Sciences,Water Science and Technology,Geography, Planning and Development

Reference68 articles.

1. April 2023. Wikipedia Statistics. https://en.wikipedia.org/wiki/Special:Statistics April 2023. Wikipedia Statistics. https://en.wikipedia.org/wiki/Special:Statistics

2. Large language models are few-shot clinical information extractors

3. Simran Arora , Patrick Lewis , Angela Fan , Jacob Kahn , and Christopher Ré. 2023. Reasoning over Public and Private Data in Retrieval-Based Systems. Transactions of Computational Linguistics (TACL) ( 2023 ). Simran Arora, Patrick Lewis, Angela Fan, Jacob Kahn, and Christopher Ré. 2023. Reasoning over Public and Private Data in Retrieval-Based Systems. Transactions of Computational Linguistics (TACL) (2023).

4. Simran Arora , Avanika Narayan , Mayee F. Chen , Laurel Orr , Neel Guha , Kush Bhatia , Ines Chami , Frederic Sala , and Christopher Ré . 2023 . Ask Me Anything: A simple strategy for prompting language models . International Conference on Learning Representations (ICLR) (2023). Simran Arora, Avanika Narayan, Mayee F. Chen, Laurel Orr, Neel Guha, Kush Bhatia, Ines Chami, Frederic Sala, and Christopher Ré. 2023. Ask Me Anything: A simple strategy for prompting language models. International Conference on Learning Representations (ICLR) (2023).

5. Simran Arora Brandon Yang Sabri Eyuboglu Avanika Narayan Andrew Hojel Immanuel Trummer and Christopher Ré. 2023. Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes. (2023). https://www.dropbox.com/scl/fi/3gt3ixdbvp986ptyz5j4t/VLDB_Revision.pdf?rlkey=mxi2kqp7rqx0frm9s7bpttwcq&dl=0 Simran Arora Brandon Yang Sabri Eyuboglu Avanika Narayan Andrew Hojel Immanuel Trummer and Christopher Ré. 2023. Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes. (2023). https://www.dropbox.com/scl/fi/3gt3ixdbvp986ptyz5j4t/VLDB_Revision.pdf?rlkey=mxi2kqp7rqx0frm9s7bpttwcq&dl=0

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3