相关论文: Magicoder: Empowering Code Generation with OSS-Ins…

Large language models (LLMs) are shown to possess a wealth of actionable knowledge that can be extracted for robot manipulation in the form of reasoning and planning. Despite the progress, most still rely on pre-defined motion primitives to…

Large language models (LLMs) have enhanced our ability to rapidly analyze and classify unstructured natural language data. However, concerns regarding cost, network limitations, and security constraints have posed challenges for their…

Large language models (LLMs) are a new and powerful tool for a wide span of applications involving natural language and demonstrate impressive code generation abilities. The goal of this work is to automatically generate tests and use these…

Large Language Models (LLMs) have transformed code completion tasks, providing context-based suggestions to boost developer productivity in software engineering. As users often fine-tune these models for specific applications, poisoning and…

The prominent large language models (LLMs) of today differ from past language models not only in size, but also in the fact that they are trained on a combination of natural language and formal language (code). As a medium between humans…

Large language models (LLMs) have been used for diverse tasks in natural language processing (NLP), yet remain under-explored for task-oriented dialogue systems (TODS), especially for end-to-end TODS. We present InstructTODS, a novel…

Converting webpage designs into code (design-to-code) plays a vital role in User Interface (UI) development for front-end developers, bridging the gap between visual design and functional implementation. While recent Multimodal Large…

The increasing development of LLMs in code generation has drawn significant attention among researchers. To enhance LLM-based code generation ability, current efforts are predominantly directed towards collecting high-quality datasets and…

This paper presents SimulatorCoder, an agent powered by large language models (LLMs), designed to generate and optimize deep neural network (DNN) accelerator simulators based on natural language descriptions. By integrating domain-specific…

The fine-tuning of open-source large language models (LLMs) for machine translation has recently received considerable attention, marking a shift towards data-centric research from traditional neural machine translation. However, the area…

ExaRanker recently introduced an approach to training information retrieval (IR) models, incorporating natural language explanations as additional labels. The method addresses the challenge of limited labeled examples, leading to…

Large language models (LLMs) excel at implementing code from functionality descriptions but struggle with algorithmic problems that require not only implementation but also identification of the suitable algorithm. Moreover, LLM-generated…

Superoptimization is the task of transforming a program into a faster one while preserving its input-output behavior. In this work, we investigate whether large language models (LLMs) can serve as superoptimizers, generating assembly…

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…

Large Language models (LLMs) are finding wide use in software engineering practice. These models are extremely data-hungry, and are largely trained on open-source (OSS) code distributed with permissive licenses. In terms of actual use…

There is a growing trend of teaching large language models (LLMs) to solve mathematical problems through coding. Existing studies primarily focus on prompting powerful, closed-source models to generate seed training data followed by…

With the capabilities of understanding and executing natural language instructions, Large language models (LLMs) can potentially act as a powerful tool for textual data augmentation. However, the quality of augmented data depends heavily on…

Despite recent progress achieved by code large language models (LLMs), their remarkable abilities are largely dependent on fine-tuning on the high-quality data, posing challenges for data collection and annotation. To address this, current…

Code translation tools (transpilers) are developed for automatic source-to-source translation. Although learning-based transpilers have shown impressive enhancement against rule-based counterparts, owing to their task-specific pre-training…

A significant amount of research is focused on developing and evaluating large language models for a variety of code synthesis tasks. These include synthesizing code from natural language, synthesizing tests from code, and synthesizing…