Related papers: Neurosymbolic Repair for Low-Code Formula Language…

Large language models such as Codex, have shown the capability to produce code for many programming tasks. However, the success rate of existing models is low, especially for complex programming tasks. One of the reasons is that language…

We have developed a symbolic algebra approach to automatically produce, verify, and optimize computer code for the Fast Multipole Method (FMM) operators. This approach allows for flexibility in choosing a basis set and kernel, and can…

With the recent advancement of Large Language Models (LLMs), generating functionally correct code has become less complicated for a wide array of developers. While using LLMs has sped up the functional development process, it poses a heavy…

Automated Program Repair (APR) has evolved significantly with the advent of Large Language Models (LLMs). Fine-tuning LLMs for program repair is a recent avenue of research, with many dimensions which have not been explored. Existing work…

Large Language Models (LLMs) show strong potential for automating model generation from natural-language descriptions. A common approach begins with an initial model generation, followed by an iterative critique-refine loop in which the…

Large language models (LLMs) have recently demonstrated strong potential for automated program repair (APR). However, existing LLM-based techniques primarily rely on coarse-grained external feedback (e.g.,test results) to guide iterative…

Large language models (LLMs) have demonstrated impressive capabilities in generating software code for high-level programming languages such as Python and C++. However, their application to hardware description languages, such as Verilog,…

Large language models (LLMs) have exhibited impressive multilingual reasoning capabilities, driven by extensive multilingual pre-training corpora and instruction fine-tuning data. However, a performance gap exists between high- and…

Large Language Models (LLMs) achieve strong performance on natural language tasks but remain unreliable in mathematical reasoning, frequently generating fluent yet logically inconsistent solutions. We present \textbf{NeuroProlog}, a…

Automated Program Repair (APR) has emerged as a promising paradigm for reducing debugging time and improving the overall efficiency of software development. Recent advances in Large Language Models (LLMs) have demonstrated their potential…

We introduce and study the problem of Continual Multilingual Learning (CML) where a previously trained multilingual model is periodically updated using new data arriving in stages. If the new data is present only in a subset of languages,…

Automatic programming attempts to minimize human intervention in the generation of executable code, and has been a long-standing challenge in the software engineering community. To advance automatic programming, researchers are focusing on…

Large Language Models (LLMs) often struggle with complex mathematical reasoning, where prose-based generation leads to unverified and arithmetically unsound solutions. Current prompting strategies like Chain of Thought still operate within…

AI assistance continues to help advance applications in education, from language learning to intelligent tutoring systems, yet current methods for providing students feedback are still quite limited. Most automatic feedback systems either…

Retrieval-Augmented Generation (RAG) significantly enhances Large Language Models (LLMs), but simultaneously exposes a critical vulnerability to knowledge poisoning attacks. Existing attack methods like PoisonedRAG remain detectable due to…

Automatic prompt engineering aims to enhance the generation quality of large language models (LLMs). Recent works utilize feedbacks generated from erroneous cases to guide the prompt optimization. During inference, they may further retrieve…

Language Model (LM) pipelines can dynamically refine their outputs against programmatic constraints. However, their effectiveness collapses when faced with competing soft constraints, leading to inefficient backtracking loops where…

Function-level code generation leverages foundation Large Language Models (LLMs) to automatically produce source code with expected functionality. It has been widely investigated and applied in intelligent programming assistants, such as…

Spell correction is still a challenging problem for low-resource languages (LRLs). While pretrained language models (PLMs) have been employed for spell correction, their use is still limited to a handful of languages, and there has been no…

Like humans, large language models (LLMs) do not always generate the best output on their first try. Motivated by how humans refine their written text, we introduce Self-Refine, an approach for improving initial outputs from LLMs through…