Related papers: Contextualized Data-Wrangling Code Generation in C…

In the wake of information overload in academia, methodologies and systems for search, recommendation, and prediction to aid researchers in identifying relevant research are actively studied and developed. Existing work, however, is limited…

Code generation models based on the pre-training and fine-tuning paradigm have been increasingly attempted by both academia and industry, resulting in well-known industrial models such as Codex, CodeGen, and PanGu-Coder. To evaluate the…

Notebooks provide an interactive environment for programmers to develop code, analyse data and inject interleaved visualizations in a single environment. Despite their flexibility, a major pitfall that data scientists encounter is…

Deep learning-based code processing models have shown good performance for tasks such as predicting method names, summarizing programs, and comment generation. However, despite the tremendous progress, deep learning models are often prone…

Software is constantly changing, requiring developers to perform several derived tasks in a timely manner, such as writing a description for the intention of the code change, or identifying the defect-prone code changes. Considering that…

Understanding neural networks is challenging in part because of the dense, continuous nature of their hidden states. We explore whether we can train neural networks to have hidden states that are sparse, discrete, and more interpretable by…

Containerization allows developers to define the execution environment in which their software needs to be installed. Docker is the leading platform in this field, and developers that use it are required to write a Dockerfile for their…

Code generation models can benefit data scientists' productivity by automatically generating code from context and text descriptions. An important measure of the modeling progress is whether a model can generate code that can correctly…

Over the last several decades, software has been woven into the fabric of every aspect of our society. As software development surges and code infrastructure of enterprise applications ages, it is now more critical than ever to increase…

While language models (LMs) have proven remarkably adept at generating code, many programs are challenging for LMs to generate using their parametric knowledge alone. Providing external contexts such as library documentation can facilitate…

Bimodal software analysis initially appeared to be within reach with the advent of large language models. Unfortunately, the complex interplay of natural language text and code in software engineering, presents unique challenges that…

Recent research has achieved impressive results on understanding and improving source code by building up on machine-learning techniques developed for natural languages. A significant advancement in natural-language understanding has come…

Visual reasoning is crucial for multimodal large language models (MLLMs) to address complex chart queries, yet high-quality rationale data remains scarce. Existing methods leveraged (M)LLMs for data generation, but direct prompting often…

Computational notebooks have become popular for Exploratory Data Analysis (EDA), augmented by LLM-based code generation and result interpretation. Effective LLM assistance hinges on selecting informative context -- the minimal set of cells…

Visual Document Understanding has become essential with the increase of text-rich visual content. This field poses significant challenges due to the need for effective integration of visual perception and textual comprehension, particularly…

Due to their ability to process long and complex contexts, LLMs can offer key benefits to the Legal domain, but their adoption has been hindered by their tendency to generate unfaithful, ungrounded, or hallucinatory outputs. While…

State of the art natural language processing tools are built on context-dependent word embeddings, but no direct method for evaluating these representations currently exists. Standard tasks and datasets for intrinsic evaluation of…

Automated program comprehension underpins many software engineering tasks, from code summarisation to clone detection. Recent deep learning models achieve strong results but typically rely on source code alone, overlooking contextual…

We introduce DA-Code, a code generation benchmark specifically designed to assess LLMs on agent-based data science tasks. This benchmark features three core elements: First, the tasks within DA-Code are inherently challenging, setting them…

Current AI-powered code assistance tools often struggle with poorly-defined problem statements that lack sufficient task context and requirements specification. Recent analysis of software engineering agents reveals that failures on such…