# Towards Zero-Shot and Few-Shot Table Question Answering using GPT-3

arXiv: https://arxiv.org/abs/2210.17284 · HTML: https://mlsanity.com/paper/2210.17284/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 16 references that are in the map.
- First posted on arXiv 31 Oct 2022.

## Builds on (most cited first, 16 of 16)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task](https://mlsanity.com/paper/1809.08887/) (2018)
- [Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning](https://mlsanity.com/paper/1709.00103/) (2017)
- [Compositional Semantic Parsing on Semi-Structured Tables](https://mlsanity.com/paper/1508.00305/) (2015)
- [TAPAS: Weakly Supervised Table Parsing via Pre-training](https://mlsanity.com/paper/2004.02349/) (2020)
- [TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data](https://mlsanity.com/paper/2005.08314/) (2020)
- [HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data](https://mlsanity.com/paper/2004.07347/) (2020)
- [TAPEX: Table Pre-training via Learning a Neural SQL Executor](https://mlsanity.com/paper/2107.07653/) (2021)
- [Neural Question Generation from Text: A Preliminary Study](https://mlsanity.com/paper/1704.01792/) (2017)
- [Unsupervised Multi-hop Question Answering by Question Generation](https://mlsanity.com/paper/2010.12623/) (2020)

## Built on by (most cited first, 4 of 4)

- [Professional Certification Benchmark Dataset: The First 500 Jobs For Large Language Models](https://mlsanity.com/paper/2305.05377/) (2023)
- [Evaluating AI Vocational Skills Through Professional Testing](https://mlsanity.com/paper/2312.10603/) (2023)
- [Impact of ChatGPT on the writing style of condensed matter physicists](https://mlsanity.com/paper/2408.17325/) (2024)
- [IntellectSeeker: A Personalized Literature Management System with the Probabilistic Model and Large Language Model](https://mlsanity.com/paper/2412.07213/) (2024)

## Abstract (arXiv)

We present very early results on using GPT-3 to perform question answering on tabular data. We find that stock pre-trained GPT-3 is able to zero-shot learn the table structure from a serialized JSON array-of-arrays representation, and able to answer lookup queries and simple comparison questions in natural language without any fine-tuning. We further find that simple prompt engineering to include few-shot static Q&A examples significantly improves accuracy. Lastly, we find that intermixing passage text improves accuracy even further on heterogeneous data. We apply our approach on a novel dataset of simple tables in newspaper infographics with promising results. Overall, we find much cause for optimism in this basic approach.