Related papers: Adaptoring: Adapter Generation to Provide an Alter…

We study the code generation behavior of instruction-tuned models built on top of code pre-trained language models when they could access an auxiliary function to implement a function. We design several ways to provide auxiliary functions…

Context: The algorithms for generating a safe fluent API are actively studied these years. A safe fluent API is the fluent API that reports incorrect chaining of the API methods as a type error to the API users. Although such a safe…

As text and code resources have expanded, large-scale pre-trained models have shown promising capabilities in code generation tasks, typically employing supervised fine-tuning with problem statement-program pairs. However, increasing model…

Third-party libraries are essential in software development as they prevent the need for developers to recreate existing functionalities. However, vulnerabilities within these libraries pose significant risks to dependent projects.…

Biological intelligence is inherently adaptive -- animals continually adjust their actions based on environmental feedback. However, creating adaptive artificial intelligence (AI) remains a major challenge. The next frontier is to go beyond…

Indexes can significantly improve search performance in relational databases. However, if the query workload changes frequently or new data updates occur continuously, it may not be worthwhile to build a conventional index upfront for query…

When designing a new API for a large project, developers need to make smart design choices so that their code base can grow sustainably. To ensure that new API components are well designed, developers can learn from existing API components.…

The availability of large idea repositories (e.g., the U.S. patent database) could significantly accelerate innovation and discovery by providing people with inspiration from solutions to analogous problems. However, finding useful…

Large language models (LMs) are typically adapted to improve performance on new contexts (\eg text prompts that define new tasks or domains) through fine-tuning or prompting. However, there is an accuracy compute tradeoff -- fine-tuning…

Many NLP applications require models to be interpretable. However, many successful neural architectures, including transformers, still lack effective interpretation methods. A possible solution could rely on building explanations from…

Large Language Models (LLMs) often struggle with code generation tasks involving niche software libraries. Existing code generation techniques with only human-oriented documentation can fail -- even when the LLM has access to web search and…

Standardized interfaces are the connecting link of today's distributed systems, facilitating access to data services in the cloud. REST APIs have been prevalent over the last years, despite several issues like over- and underfetching of…

We introduce torchbearer, a model fitting library for pytorch aimed at researchers working on deep learning or differentiable programming. The torchbearer library provides a high level metric and callback API that can be used for a wide…

In an era of widespread influence of Natural Language Processing (NLP), there have been multiple research efforts to supplant traditional manual coding techniques with automated systems capable of generating solutions autonomously. With…

Self-adaptation solutions need to periodically monitor, reason about, and adapt a running system. The adaptation step involves generating an adaptation strategy and applying it to the running system whenever an anomaly arises. In this…

Automatic code transformation in which transformations are tuned for specific applications and contexts are difficult to achieve in an accessible manner. In this paper, we present an approach to build application specific code…

Nowadays, it has become a basic need to reuse existing Application Programming Interface (API), Class Libraries, and frameworks for rapid software development. Software developers often reuse this by calling the respective APIs or…

Programmers often search for usage examples for API methods. A tool that could generate realistic, idiomatic, and contextual usage examples for one or more APIs would be immensely beneficial to developers. Such a tool would relieve the need…

Large Language Models (LLMs) have shown high capabilities in several software development-related tasks such as program repair, documentation, code refactoring, debugging, and testing. However, training these models requires massive amount…

While extreme-scale language models have demonstrated exceptional performance on a variety of language tasks, the degree of control over these language models through pure prompting can often be limited. Directly fine-tuning such language…