Related papers: Automating TODO-missed Methods Detection and Patch…

Several Deep Learning (DL)-based techniques have been proposed to automate code review. Still, it is unclear the extent to which these approaches can recommend quality improvements as a human reviewer. We study the similarities and…

Data scientists develop ML pipelines in an iterative manner: they repeatedly screen a pipeline for potential issues, debug it, and then revise and improve its code according to their findings. However, this manual process is tedious and…

Defect Prevention is the most critical but most neglected component of the software quality assurance in any project. If applied at all stages of software development, it can reduce the time, cost and resources required to engineer a high…

Code review is a common process that is used by developers, in which a reviewer provides useful comments or points out defects in the submitted source code changes via pull request. Code review has been widely used for both industry and…

Technical debt (TD) refers to the long-term costs associated with suboptimal design or code decisions in software development, often made to meet short-term delivery goals. Self-Admitted Technical Debt (SATD) occurs when developers…

Comments in software are critical for maintenance and reuse. But apart from prescriptive advice, there is little practical support or quantitative understanding of what makes a comment useful. In this paper, we introduce the task of…

Many users and contributors of large open-source projects report software defects or enhancement requests (known as bug reports) to the issue-tracking systems. However, they sometimes report issues that have already been reported. First,…

In this technical report, we introduce Effidit (Efficient and Intelligent Editing), a digital writing assistant that facilitates users to write higher-quality text more efficiently by using artificial intelligence (AI) technologies.…

Code completion is an important feature of integrated development environments (IDEs). It allows developers to produce code faster, especially novice ones who are not fully familiar with APIs and others code. Previous works on code…

Motivation: Code understandability is crucial in software development, as developers spend 58% to 70% of their time reading source code. Improving it can improve productivity and reduce maintenance costs. Problem: Experimental studies often…

In this paper we present an approach for localizing steps of procedural activities in narrated how-to videos. To deal with the scarcity of labeled data at scale, we source the step descriptions from a language knowledge base (wikiHow)…

Code completion aims to help improve developers' productivity by suggesting the next code tokens from a given context. Various approaches have been proposed to incorporate abstract syntax tree (AST) information for model training, ensuring…

Task-oriented dialogue systems have been plagued by the difficulties of obtaining large-scale and high-quality annotated conversations. Furthermore, most of the publicly available datasets only include written conversations, which are…

The tidal wave of advancements in Large Language Models (LLMs) has led to their swift integration into application-level logic. Many software systems now use prompts to interact with these black-box models, combining natural language with…

We propose a variant of chain of thought (CoT) prompting called Program Trace Prompting that makes explanations more observable while preserving the power, generality and flexibility of CoT. In our approach, few-shot CoT demonstrations are…

While existing code large language models (code LLMs) exhibit impressive capabilities in code generation, their autoregressive sequential generation inherently lacks reversibility. This limitation hinders them from timely correcting…

A source code difference (diff) indicates changes made by comparing new and old source codes, and it can be utilized in code reviews to help developers understand the changes made to the code. Although many diff generation methods have been…

Deepfake (DF) detectors face significant challenges when deployed in real-world environments, particularly when encountering test samples deviated from training data through either postprocessing manipulations or distribution shifts. We…

Supervised Fine-Tuning (SFT) Large Language Models (LLM) fundamentally rely on high-quality training data. While data selection and data synthesis are two common strategies to improve data quality, existing approaches often face limitations…

Whether intermediate reasoning is computationally useful or merely explanatory depends on whether chain-of-thought (CoT) tokens contain task-relevant information. We present a mechanistic causal analysis of CoT on GSM8K using activation…