Large pre-trained language models such as GPT-3 [10], Codex [11], and Google's language
model [7] are now capable of generating code from natural language specifications of …

A great part of software development involves conceptualizing or communicating the
underlying procedures and logic that needs to be expressed in programs. One major …

We introduce Magicoder, a series of fully open-source (code, weights, and data) Large
Language Models (LLMs) for code that significantly closes the gap with top code models …

To release developers from time-consuming software development, many approaches have
been proposed to generate source code automatically according to software requirements …

Generative models for source code are an interesting structured prediction problem,
requiring to reason about both hard syntactic and semantic constraints as well as about …

Deep neural networks (DNN) have been shown to be notoriously brittle to small
perturbations in their input data. This problem is analogous to the over-fitting problem in test …

Developers nowadays have to contend with a growing number of APIs. While in the long-
term they are very useful to developers, many modern APIs have an incredibly steep …

We describe an inductive logic programming (ILP) approach called learning from failures. In
this approach, an ILP system (the learner) decomposes the learning problem into three …

While many mainstream languages such as Java, Python, and C# increasingly incorporate
functional APIs to simplify programming and improve parallelization/performance, there are …

We consider the problem of neural semantic parsing, which translates natural language
questions into executable SQL queries. We introduce a new mechanism, execution …