Program Synthesis

By Sumit Gulwani, Oleksandr Polozov, Rishabh Singh. 2017

695 citations recorded by the source corpus.

Subfields: Hardware and Architecture, Natural Language Processing, Code Generation & Program Synthesis

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Hardware and Architecture

In Natural Language Processing

In Code Generation & Program Synthesis

Citations in the corpus

Competition-level code generation with AlphaCode (2022, background): “Gulwani et al. (2017) provides an excellent survey of these program synthesis approaches.”
Program Synthesis with Large Language Models (2021, neutral): “…specification: in contrast to classical work on program synthesis that specifies the program using logical constraints or input-output examples [Gulwani et al., 2017], a program can be specified by a short natural language description, possibly combined with a few (e.g., 2 or 3) input-output…”
InCoder: A Generative Model for Code Infilling and Synthesis (2022, methodology): “Machine Learning for Program Synthesis Program synthesis approaches directly generate programs from a specification of functionality [29].”
CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis (2022, background): “Program Synthesis While program synthesis has a long history, two inherent challenges remain unsolved: (1) intractability of the program space and (2) difficulty in accurately expressing user intent (Manna & Waldinger, 1971; Gulwani et al., 2017).”
Large Language Models Are Human-Level Prompt Engineers (2022, background): “Program Synthesis Program synthesis involves the automatic search over a “program space” to find a program satisfying a particular specification (Gulwani et al., 2017).”
An Introduction to Probabilistic Programming (2018, background): “This is the central idea in the work of Perov and Wood (2016) whose use of probabilistic programming is what distinguishes their work from the related literature (Gulwani et al., 2017; Hwang et al., 2011; Liang et al., 2010).”
MultiPL-E: A Scalable and Polyglot Approach to Benchmarking Neural Code Generation (2023, background): “Code generation has long been a task of interest: there is extensive work on program synthesis [11], [12], [13] using both symbolic and neuro-symbolic approaches.”
A Hazard Analysis Framework for Code Synthesis Large Language Models (2022, neutral): “Deriving from programming language synthesis techniques may lead the way on how this can be carried out [9, 12, 16, 18, 32].”
CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation (2021, methodology): “The program synthesis [47, 58, 62, 74, 17, 40, 90] extends the text-to-code generation task aims to generate programs from a specification [21], such as pseudocode, natural language description, and input/output examples.”
Measuring Coding Challenge Competence With APPS (2021, background): “Inductive synthesis from example input-output behavior can provide an alternative to formal speciﬁcation (Cai et al., 2017; Gulwani et al., 2017), but it is often hard to full specify behavior with examples, as any machine learning practitioner is well-aware.”
A Conversational Paradigm for Program Synthesis (2022, background): “Some have called it the holy grail of computer science (Manna and Waldinger, 1971; Gulwani et al., 2017).”
A Survey of Large Language Models (2023, neutral): “, code) that satisfy specific conditions, called code synthesis [344].”
Structural Language Models of Code (2019, background): “Program Generation Learning to generate programs is one of the oldest problems in machine learning (Waldinger & Lee, 1969) and has been considered by some as the “holy grail of computer science” (Pnueli & Rosner, 1989; Gulwani et al., 2017).”
Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation (2023, background): “Automatically generating programs that accurately correspond to user intents is a long-standing challenge in computer science known as program synthesis [20].”
Neurosymbolic Programming (2021, methodology): “For example, Srivastava et al. (2020) combine neural language modeling with inductive program synthesis Gulwani et al., 2017 to learn a generative model of programs that both guarantees consistency with the demonstrations and optimizes natural language alignment.”
BUSTLE: Bottom-up program-Synthesis Through Learning-guided Exploration (2020, background): “For surveys on program synthesis and machine learning for software engineering, see Gottschlich et al. (2018); Solar-Lezama (2018); Gulwani et al. (2017); Allamanis et al. (2018).”