Related papers: Reimplementing the Wheel: Teaching Compilers with …

An optimizing compiler consists of a front end parsing a textual programming language into an intermediate representation (IR), a middle end performing optimizations on the IR, and a back end lowering the IR to a target representation (TR)…

Large language models (LLMs) have achieved notable success in code generation. However, they still frequently produce uncompilable output because their next-token inference procedure does not model formal aspects of code. Although…

Training LLMs for code-related tasks typically depends on high-quality code-documentation pairs, which are costly to curate and often scarce for niche programming languages. We introduce BatCoder, a self-supervised reinforcement learning…

Grammar induction has made significant progress in recent years. However, it is not clear how the application of induced grammar could enhance practical performance in downstream tasks. In this work, we introduce an unsupervised grammar…

Large language models (LLMs) are being increasingly adopted for programming work. Prior work shows that while LLMs accelerate task completion for professional programmers, beginning programmers struggle to prompt models effectively.…

Computing educators face significant challenges in providing timely support to students, especially in large class settings. Large language models (LLMs) have emerged recently and show great promise for providing on-demand help at a large…

While large models achieve impressive results, their learning dynamics are far from understood. Many domains of interest, such as natural language syntax, coding languages, arithmetic problems, are captured by context-free grammars (CFGs).…

Code summarization (CS) is becoming a promising area in recent language understanding, which aims to generate sensible human language automatically for programming language in the format of source code, serving in the most convenience of…

Scientific machine learning often requires combining known physics with unknown parameters or correction terms learned from data. Existing approaches either ignore known structure, encode it as a soft penalty, or require hand-written…

Introductory programming courses often emphasize mastering syntax and basic constructs before progressing to more complex and interesting programs. This bottom-up approach can be frustrating for novices, shifting the focus away from problem…

Compilers are used to run programs that are written in a range of designs from text to executable formats. With the advent of the internet, studies related to the development of cloud based compilers are being carried out. There is a…

Large Language Models (LLMs) have achieved remarkable performance across various reasoning tasks, yet post-training is constrained by inefficient sample utilization and inflexible difficulty samples processing. To address these limitations,…

The place and role of parsing analysis in formation of professional informatics competences of future informatics teachers is determined. Separated automation tools for lexical (lex) and syntax (yacc) analysis invariant to the programming…

The ability to compose code in a modular fashion is important to the construction of large programs. In the logic programming setting, it is desirable that such capabilities be realized through logic-based devices. We describe an approach…

Recently generating natural language explanations has shown very promising results in not only offering interpretable explanations but also providing additional information and supervision for prediction. However, existing approaches…

Mechanistic interpretability aims to explain neural model behaviour by reverse-engineering learned computational structure into human-understandable components. Without a formal framework, however, mechanistic explanations cannot be…

Large Language Models (LLMs) have demonstrated impressive capabilities in understanding and generating codes. Due to these capabilities, many recent methods are proposed to automatically refine the codes with LLMs. However, we should…

Compilers, while essential, are notoriously complex systems that demand prohibitively expensive human expertise to develop and maintain. The recent advancements in Large Language Models (LLMs) offer a compelling new paradigm: Neural…

A compiler processes the code written in a high level language and produces machine executable code. The compiler writers often face the challenge of keeping the compilation times reasonable. That is because aggressive optimization passes…

Text generation under constraints have seen increasing interests in natural language processing, especially with the rapidly improving capabilities of large language models. However, existing benchmarks for constrained generation usually…