Related papers: Learning Bug Context for PyTorch-to-JAX Translatio…

Ever since Large Language Models (LLMs) and related applications have become broadly available, several studies investigated their potential for assisting educators and supporting students in higher education. LLMs such as Codex, GPT-3.5,…

Context: An increasing number of software systems are written in multiple programming languages (PLs), which are called multi-programming-language (MPL) systems. MPL bugs (MPLBs) refers to the bugs whose resolution involves multiple PLs.…

LLMs excel at code generation from English prompts, but this progress has not extended to low-resource languages. We address Bangla-to-Python code generation by introducing BanglaCodeAct, an agent-based framework that leverages multi-agent…

Large Language Models (LLMs) have shown promise in multiple software engineering tasks including code generation, program repair, code summarisation, and test generation. Fault localisation is instrumental in enabling automated debugging…

Pretrained large language models (LLMs) are increasingly utilized across a wide range of natural language processing (NLP) tasks due to their impressive capabilities as few-shot learners. Recent techniques, such as chain-of-thought (CoT)…

The growing dependence on Large Language Models (LLMs) for finishing user instructions necessitates a comprehensive understanding of their robustness to complex task completion in real-world situations. To address this critical need, we…

This paper studies recent developments in large language models' (LLM) abilities to pass assessments in introductory and intermediate Python programming courses at the postsecondary level. The emergence of ChatGPT resulted in heated debates…

Training LLMs for low-resource languages usually utilizes data augmentation from English using machine translation (MT). This, however, brings a number of challenges to LLM training: there are large costs attached to translating and…

This paper explores the efficacy of large language models (LLMs) for Persian. While ChatGPT and consequent LLMs have shown remarkable performance in English, their efficiency for more low-resource languages remains an open question. We…

Document-to-table (Doc2Table) extraction derives structured tables from unstructured documents under a target schema, enabling reliable and verifiable SQL-based data analytics. Although large language models (LLMs) have shown promise in…

Bug reports contain the information developers need to triage and fix software bugs. However, unclear, incomplete, or ambiguous information may lead to delays and excessive manual effort spent on bug triage and resolution. In this paper, we…

Large language models (LLMs) exhibit in-context learning abilities which enable the same model to perform several tasks without any task-specific training. In contrast, traditional adaptation approaches, such as fine-tuning, modify the…

Existing large language model (LLM) evaluation benchmarks primarily focus on English, while current multilingual tasks lack parallel questions that specifically assess cross-linguistic reasoning abilities. This dual limitation makes it…

Large Language Models (LLMs) are increasingly treated as universal, general-purpose solutions across NLP tasks, particularly in English. But does this assumption hold for low-resource, morphologically rich languages such as Sanskrit? We…

Background: Bug reports are essential to the software development life cycle. They help developers track and resolve issues, but are often difficult to process due to their complexity, which can delay resolution and affect software quality.…

Multimodal Large Language Models (MLLMs) have achieved great success in Speech-to-Text Translation (S2TT) tasks. However, current research is constrained by two key challenges: language coverage and efficiency. Most of the popular S2TT…

Low-precision training reduces computational cost and produces efficient models. Recent research in developing new low-precision training algorithms often relies on simulation to empirically evaluate the statistical effects of quantization…

Code repair is a fundamental task in software development, facilitating efficient bug resolution and software maintenance. Although large language models (LLMs) have demonstrated considerable potential in automated code repair, their…

Current soft prompt methods yield limited performance when applied to small-sized models (fewer than a billion parameters). Deep prompt-tuning, which entails prepending parameters in each layer for enhanced efficacy, presents a solution for…

Large language models (LLMs) are increasingly used for creative tasks such as literary translation. Yet translational creativity remains underexplored and is rarely evaluated at scale, while source-text comprehension is typically studied in…