Related papers: Reimplementing the Wheel: Teaching Compilers with …

The mechanisms of comprehension during language processing remains an open question. Classically, building the meaning of a linguistic utterance is said to be incremental, step-by-step, based on a compositional process. However, many…

We demonstrate that a dependency parser can be built using a credit assignment compiler which removes the burden of worrying about low-level machine learning details from the parser implementation. The result is a simple parser which…

We introduce SelfExplain, a novel self-explaining model that explains a text classifier's predictions using phrase-based concepts. SelfExplain augments existing neural classifiers by adding (1) a globally interpretable layer that identifies…

Large Language Models (LLMs) have upended decades of pedagogy in computing education. Students previously learned to code through \textit{writing} many small problems with less emphasis on code reading and comprehension. Recent research has…

Self-correction has demonstrated potential in code generation by allowing language models to revise and improve their outputs through successive refinement. Recent studies have explored prompting-based strategies that incorporate…

The size and complexity of software applications is increasing at an accelerating pace. Source code repositories (along with their dependencies) require vast amounts of labor to keep them tested, maintained, and up to date. As the…

Current language models achieve low perplexity but their resulting generations still suffer from toxic responses, repetitiveness and contradictions. The standard language modeling setup fails to address these issues. In this paper, we…

Multitier programming languages reduce the complexity of developing distributed systems by developing the distributed system in a single coherent code base. The compiler or the runtime separate the code for the components of the distributed…

Code summary generation is the task of writing natural language descriptions of a section of source code. Recent advances in Large Language Models (LLMs) and other AI-based technologies have helped make automatic code summarization a…

Binary decompilation is a critical reverse engineering task aimed at reconstructing high-level source code from stripped executables. Although Large Language Models (LLMs) have recently shown promise, they often suffer from "logical…

Code generation maps a program description to executable source code in a programming language. Existing approaches mainly rely on a recurrent neural network (RNN) as the decoder. However, we find that a program contains significantly more…

To refactor already working code while keeping reliability, compatibility and perhaps security, we can borrow ideas from micropass/nanopass compilers. By treating the procedure of software refactoring as composing code transformations, and…

Quantum programs today are written at a low level of abstraction - quantum circuits akin to assembly languages - and the unitary parts of even advanced quantum programming languages essentially function as circuit description languages.…

Background: The growing demand for efficient and deployable language models has led to increased interest in Small Language Models (SLMs). However, existing research remains fragmented, lacking a unified lifecycle perspective. Objective:…

Integrating free-text explanations to in-context learning of large language models (LLM) is shown to elicit strong reasoning capabilities along with reasonable explanations. In this paper, we consider the problem of leveraging the…

Large pre-trained language models have recently been expanded and applied to programming language tasks with great success, often through further pre-training of a strictly-natural language model--where training sequences typically contain…

Developing soft circuits from individual soft logic gates poses a unique challenge: with increasing numbers of logic gates, the design and implementation of circuits leads to inefficiencies due to mathematically unoptimized circuits and…

Large Language Models (LLMs) have demonstrated great promise in generating code, especially when used inside an evolutionary computation framework to iteratively optimize the generated algorithms. However, in some cases they fail to…

Transformers have been shown to emulate logical deduction over natural language theories (logical rules expressed in natural language), reliably assigning true/false labels to candidate implications. However, their ability to generate…

Several recent advances in AI systems solve problems by providing a "scaffolding" program that structures multiple calls to language models (LMs) to generate better outputs. A scaffolding program is written in a programming language such as…