Related papers: Latent Idiom Recognition for a Minimalist Function…

Language Identification (LID) is an important component of many multilingual natural language processing pipelines, where it facilitates corpus curation, training data analysis, and cross-lingual evaluation of large language models. Despite…

Micro-core architectures combine many simple, low memory, low power-consuming CPU cores onto a single chip. Potentially providing significant performance and low power consumption, this technology is not only of great interest in embedded,…

In this paper, we introduce the problem of rewriting finite formal languages using syntactic macros such that the rewriting is minimal in size. We present polynomial-time algorithms to solve variants of this problem and show their…

The rapid advancement of large language models has unlocked remarkable capabilities across a diverse array of natural language processing tasks. However, the considerable differences among available LLMs-in terms of cost, performance, and…

Code-LLMs, LLMs pre-trained on large code corpora, have shown great progress in learning rich representations of the structure and syntax of code, successfully using it to generate or classify code fragments. At the same time, understanding…

Program classification can be regarded as a high-level abstraction of code, laying a foundation for various tasks related to source code comprehension, and has a very wide range of applications in the field of software engineering, such as…

Machine learning algorithms are commonly specified in linear algebra (LA). LA expressions can be rewritten into more efficient forms, by taking advantage of input properties such as sparsity, as well as program properties such as common…

Pythonic code is idiomatic code that follows guiding principles and practices within the Python community. Offering performance and readability benefits, Pythonic code is claimed to be widely adopted by experienced Python developers, but…

In this paper we explore how machine learning techniques can be applied to the discovery of efficient mathematical identities. We introduce an attribute grammar framework for representing symbolic expressions. Given a set of grammar rules…

Large language models (LLMs) have shown great potential in code-related tasks, yet open-source models lag behind their closed-source counterparts. To bridge this performance gap, existing methods generate vast amounts of synthetic data for…

The practice of unit testing enables programmers to obtain automated feedback on whether a currently edited program is consistent with the expectations specified in test cases. Feedback is most valuable when it happens immediately, as…

Large language models (LLMs) offer substantial promise for text classification in political science, yet their effectiveness often depends on high-quality prompts and exemplars. To address this, we introduce a three-stage framework that…

There is a vast gap in the quality of IDE tooling between static languages like Java and dynamic languages like Python or JavaScript. Modern frameworks and libraries in these languages heavily use their dynamic capabilities to achieve the…

Large language models (LLMs) are renowned for their extensive linguistic knowledge and strong generalization capabilities, but their high computational demands make them unsuitable for resource-constrained environments. In contrast, small…

Linear algebra computations are foundational for neural networks and machine learning, often handled through arrays. While many functional programming languages feature lists and recursion, arrays in linear algebra demand constant-time…

Personalizing jargon detection and explanation is essential for making technical documents accessible to readers with diverse disciplinary backgrounds. However, tailoring models to individual users typically requires substantial annotation…

In recent years, text classification methods based on neural networks and pre-trained models have gained increasing attention and demonstrated excellent performance. However, these methods still have some limitations in practical…

We present a comprehensive evaluation of the ability of large language models (LLMs) to process culturally grounded language, specifically to understand and pragmatically use figurative expressions that encode local knowledge and cultural…

Context: Having domain models derived from textual specifications has proven to be very useful in the early phases of software engineering. However, creating correct domain models and establishing clear links with the textual specification…

Training with larger mini-batches improves the convergence rate and can yield superior performance. However, training with large mini-batches becomes prohibitive for Large Language Models (LLMs), due to the large GPU memory requirement. To…