相关论文: CodeLL: A Lifelong Learning Dataset to Support the…

Large Language Models (LLMs) have been widely employed in programming language analysis to enhance human productivity. Yet, their reliability can be compromised by various code distribution shifts, leading to inconsistent outputs. While…

Automatically generating webpage code from webpage designs can significantly reduce the workload of front-end developers, and recent Multimodal Large Language Models (MLLMs) have shown promising potential in this area. However, our…

Large Language Models (LLMs) are predominantly assessed based on their common sense reasoning, language comprehension, and logical reasoning abilities. While models trained in specialized domains like mathematics or coding have demonstrated…

Tool learning has emerged as a crucial capability for large language models (LLMs) to solve complex real-world tasks through interaction with external tools. Existing approaches face significant challenges, including reliance on…

Large language models (LLMs) have been touted to enable increased productivity in many areas of today's work life. Scientific research as an area of work is no exception: the potential of LLM-based tools to assist in the daily work of…

The advent of Large Language Models (LLMs) has significantly advanced the field of automated code generation. LLMs rely on large and diverse datasets to learn syntax, semantics, and usage patterns of programming languages. For low-resource…

Code changes are an integral part of the software development process. Many code changes are meant to improve the code without changing its functional behavior, e.g., refactorings and performance improvements. Unfortunately, validating…

The advent of Large Language Models (LLMs) has revolutionized various domains of artificial intelligence, including the realm of software engineering. In this research, we evaluate the efficacy of pre-trained LLMs in replicating the tasks…

This paper introduces the first, open source software library for Constraint Consistent Learning (CCL). It implements a family of data-driven methods that are capable of (i) learning state-independent and -dependent constraints, (ii)…

Existing document-level machine translation resources are only available for a handful of languages, mostly high-resourced ones. To facilitate the training and evaluation of document-level translation and, more broadly, long-context…

Concerns about benchmark leakage in large language models for code (Code LLMs) have raised issues of data contamination and inflated evaluation metrics. The diversity and inaccessibility of many training datasets make it difficult to…

Large Language Models (LLMs) often suffer from performance degradation when faced with domain shifts, primarily due to catastrophic forgetting. In this work, we propose KILO (Knowledge-Instructed Learning for Continual Adaptation), a novel…

Pretrained language models (PTLMs) are typically learned over a large, static corpus and further fine-tuned for various downstream tasks. However, when deployed in the real world, a PTLM-based model must deal with data distributions that…

Language models (LMs) built upon deep neural networks (DNNs) have recently demonstrated breakthrough effectiveness in software engineering tasks such as code generation, completion, and repair. This has paved the way for the emergence of…

Despite various approaches being employed to detect vulnerabilities, the number of reported vulnerabilities shows an upward trend over the years. This suggests the problems are not caught before the code is released, which could be caused…

Multimodal learning, a rapidly evolving field in artificial intelligence, seeks to construct more versatile and robust systems by integrating and analyzing diverse types of data, including text, images, audio, and video. Inspired by the…

Bug fixing and code generation have been core research topics in software development for many years. The recent explosive growth in Large Language Models has completely transformed these spaces, putting in reach incredibly powerful tools…

The performance of automatic code documentation generation models depends critically on the quality of the training data used for supervision. However, most existing code documentation datasets are constructed through large scale scraping…

There is a growing need for Large Language Models (LLMs) to effectively use tools and external Application Programming Interfaces (APIs) to plan and complete tasks. As such, there is tremendous interest in methods that can acquire…

Lifelong learning enables large language models (LLMs) to adapt to evolving information by continually updating their internal knowledge. An ideal system should support efficient, wide-ranging updates while preserving existing capabilities…