# WikiCoder: Learning to Write Knowledge-Powered Code

arXiv: https://arxiv.org/abs/2303.08574 · HTML: https://mlsanity.com/paper/2303.08574/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 31 references that are in the map.
- First posted on arXiv 15 Mar 2023.

## Builds on (most cited first, 12 of 12)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Knowledge Graphs](https://mlsanity.com/paper/2003.02320/) (2020)
- [DeepCoder: Learning to Write Programs](https://mlsanity.com/paper/1611.01989/) (2016)
- [RobustFill: Neural Program Learning under Noisy I/O](https://mlsanity.com/paper/1703.07469/) (2017)
- [Neural-Guided Deductive Search for Real-Time Program Synthesis from Examples](https://mlsanity.com/paper/1804.01186/) (2018)
- [TF-Coder: Program Synthesis for Tensor Manipulations](https://mlsanity.com/paper/2003.09040/) (2020)
- [Automatic Program Synthesis of Long Programs with a Learned Garbage Collector](https://mlsanity.com/paper/1809.04682/) (2018)
- [Neural Program Search: Solving Programming Tasks from Description and Examples](https://mlsanity.com/paper/1802.04335/) (2018)
- [Querying Knowledge Graphs by Example Entity Tuples](https://mlsanity.com/paper/1311.2100/) (2013)
- [Synthesizing Analytical SQL Queries from Computation Demonstration](https://mlsanity.com/paper/2204.07102/) (2022)
- [Deep API Programmer: Learning to Program with APIs](https://mlsanity.com/paper/1704.04327/) (2017)

## Abstract (arXiv)

We tackle the problem of automatic generation of computer programs from a few pairs of input-output examples. The starting point of this work is the observation that in many applications a solution program must use external knowledge not present in the examples: we call such programs knowledge-powered since they can refer to information collected from a knowledge graph such as Wikipedia. This paper makes a first step towards knowledge-powered program synthesis. We present WikiCoder, a system building upon state of the art machine-learned program synthesizers and integrating knowledge graphs. We evaluate it to show its wide applicability over different domains and discuss its limitations. WikiCoder solves tasks that no program synthesizers were able to solve before thanks to the use of knowledge graphs, while integrating with recent developments in the field to operate at scale.