Program Synthesis

137 papers with code • 3 benchmarks • 5 datasets

Program synthesis is the process of automatically generating a program or code snippet that satisfies a given specification or set of requirements. This can include generating code from a formal specification, a natural language description, or example inputs and outputs. The primary goal of program synthesis is to minimize human intervention in the coding process, reduce errors, and improve productivity.

Program synthesis often involves the use of advanced algorithms, artificial intelligence, and machine learning techniques to search the space of possible programs that meet the given constraints. This process can be guided by a variety of techniques, such as constraint solving, symbolic execution, and genetic algorithms.

Libraries

Use these libraries to find Program Synthesis models and implementations

WatChat: Explaining perplexing programs by debugging mental models

kach/watchat 8 Mar 2024

Often, a good explanation for a program's unexpected behavior is a bug in the programmer's code.

1
08 Mar 2024

Constrained Decoding for Code Language Models via Efficient Left and Right Quotienting of Context-Sensitive Grammars

amazon-science/incremental-parsing 28 Feb 2024

Large Language Models are powerful tools for program synthesis and advanced auto-completion, but come with no guarantee that their output code is syntactically correct.

5
28 Feb 2024

HumanEval on Latest GPT Models -- 2024

daniel442li/gpt-human-eval 20 Feb 2024

In 2023, we are using the latest models of GPT-4 to advance program synthesis.

1
20 Feb 2024

SwissNYF: Tool Grounded LLM Agents for Black Box Setting

iclr-dummy-user/swissnyf 15 Feb 2024

Therefore, we harness the program synthesis capabilities of LLMs to strategize tool usage in black-box settings, ensuring solutions are verified prior to implementation.

3
15 Feb 2024

Pix2Code: Learning to Compose Neural Visual Concepts as Programs

ml-research/pix2code 13 Feb 2024

The challenge in learning abstract concepts from images in an unsupervised fashion lies in the required integration of visual perception and generalizable relational reasoning.

5
13 Feb 2024

Opening the AI black box: program synthesis via mechanistic interpretability

ejmichaud/neural-verification 7 Feb 2024

We present MIPS, a novel method for program synthesis based on automated mechanistic interpretability of neural networks trained to perform the desired task, auto-distilling the learned algorithm into Python code.

6
07 Feb 2024

ReGAL: Refactoring Programs to Discover Generalizable Abstractions

esteng/regal_program_learning 29 Jan 2024

While large language models (LLMs) are increasingly being used for program synthesis, they lack the global view needed to develop useful abstractions; they generally predict programs one at a time, often repeating the same functionality.

10
29 Jan 2024

DALex: Lexicase-like Selection via Diverse Aggregation

andrewni420/dalex 23 Jan 2024

Lexicase selection has been shown to provide advantages over other selection algorithms in several areas of evolutionary computation and machine learning.

0
23 Jan 2024

Analyzing the Effectiveness of Large Language Models on Text-to-SQL Synthesis

cuplv/text-to-sql-wizardcoder 22 Jan 2024

This study investigates various approaches to using Large Language Models (LLMs) for Text-to-SQL program synthesis, focusing on the outcomes and insights derived.

38
22 Jan 2024

CodeScholar: Growing Idiomatic Code Examples

tart-proj/codescholar 23 Dec 2023

A tool that could generate realistic, idiomatic, and contextual usage examples for one or more APIs would be immensely beneficial to developers.

9
23 Dec 2023