相关论文: Delving into Commit-Issue Correlation to Enhance C…

State-of-the-art machine translation models are still not on par with human translators. Previous work takes human interactions into the neural machine translation process to obtain improved results in target languages. However, not all…

System messages play a crucial role in interactions with large language models (LLMs), often serving as prompts to initiate conversations. Through system messages, users can assign specific roles, perform intended tasks, incorporate…

Applying machine learning to tasks that operate with code changes requires their numerical representation. In this work, we propose an approach for obtaining such representations during pre-training and evaluate them on two different…

The recent advancement of Artificial Intelligence Generated Content (AIGC) has led to significant strides in modeling human interaction, particularly in the context of multimodal dialogue. While current methods impressively generate…

Code commit messages can contain useful information on why a developer has made a change. However, the presence and structure of rationale in real-world code commit messages is not well studied. Here, we detail the creation of a labelled…

Context: The increasing reliance on Code Generation Tools (CGTs), such as Windsurf and GitHub Copilot, are revamping programming workflows and raising critical questions about fairness and inclusivity. While CGTs offer potential…

We report on a large-scale empirical study investigating the relevance of socio-technical congruence over key basic software quality metrics, namely, bugs and churn. In particular, we explore whether alignment or misalignment of social…

A robust evaluation metric has a profound impact on the development of text generation systems. A desirable metric compares system output against references based on their semantics rather than surface forms. In this paper we investigate…

In text generation evaluation, many practical issues, such as inconsistent experimental settings and metric implementations, are often ignored but lead to unfair evaluation and untenable conclusions. We present CoTK, an open-source toolkit…

Developers create software branches for tentative feature addition and bug fixing, and periodically merge branches to release software with new features or repairing patches. When the program edits from different branches textually overlap…

Language models are not accurate in numerical problems. Their architecture does not allow for anything less than a probabilistic next word. This paper introduces ComputeGPT: an approach of creating a chat model able to answer computational…

The size and complexity of software applications is increasing at an accelerating pace. Source code repositories (along with their dependencies) require vast amounts of labor to keep them tested, maintained, and up to date. As the…

AI creation, such as poem or lyrics generation, has attracted increasing attention from both industry and academic communities, with many promising models proposed in the past few years. Existing methods usually estimate the outputs based…

Understanding the reasons behind past code changes is critical for many software engineering tasks, including refactoring and reviewing code, diagnosing bugs, and implementing new features. Unfortunately, locating and reconstructing this…

Large Language Models (LLMs) possess human-level cognitive and decision-making capabilities, making them a key technology for 6G. However, applying LLMs to the communication domain faces three major challenges: 1) Inadequate communication…

The robotics community has consistently aimed to achieve generalizable robot manipulation with flexible natural language instructions. One primary challenge is that obtaining robot trajectories fully annotated with both actions and texts is…

Commit Classification(CC) is an important task in software maintenance since it helps software developers classify code changes into different types according to their nature and purpose. This allows them to better understand how their…

We present a method to control a text-to-image generative model to produce training data useful for supervised learning. Unlike previous works that employ an open-loop approach and pre-define prompts to generate new data using either a…

Existing works on outline-conditioned text generation typically aim to generate text using provided outlines as rough sketches, such as keywords and phrases. However, these approaches make it challenging to control the quality of text…

Participant recruitment based on unstructured medical texts such as clinical notes and radiology reports has been a challenging yet important task for the cohort establishment in clinical research. Recently, Large Language Models (LLMs)…