Related papers: Learning to Mine Aligned Code and Natural Language…
Creating programs to correctly manipulate data is a difficult task, as the underlying programming languages and APIs can be challenging to learn for many users who are not skilled programmers. Large language models (LLMs) demonstrate…
The ability to match pieces of code to their corresponding natural language descriptions and vice versa is fundamental for natural language search interfaces to software repositories. In this paper, we propose a novel multi-perspective…
Abundant data is the key to successful machine learning. However, supervised learning requires annotated data that are often hard to obtain. In a classification task with limited resources, Active Learning (AL) promises to guide annotators…
Software developers often resort to Stack Overflow (SO) to fill their programming needs. Given the abundance of relevant posts, navigating them and comparing different solutions is tedious and time-consuming. Recent work has proposed to…
In this paper, we propose a novel word-alignment-based method to solve the FAQ-based question answering task. First, we employ a neural network model to calculate question similarity, where the word alignment between two questions is used…
Utilizing code snippets on Stack Overflow (SO) is a common practice among developers for problem-solving. Although SO code snippets serve as valuable resources, it is important to acknowledge their imperfections, reusing problematic code…
Code summarization generates brief natural language description given a source code snippet, while code retrieval fetches relevant source code given a natural language query. Since both tasks aim to model the association between natural…
We propose using natural language outlines as a novel modality and interaction surface for providing AI assistance to developers throughout the software development process. An NL outline for a code function comprises multiple statements…
On Stack Overflow, developers can not only browse question posts to solve their programming problems but also gain expertise from the question posts to help improve their programming skills. Therefore, improving the quality of question…
Alignment methodologies have emerged as a critical pathway for enhancing language model alignment capabilities. While SFT (supervised fine-tuning) accelerates convergence through direct token-level loss intervention, its efficacy is…
Aligning large language models (LLMs) to human preferences is a crucial step in building helpful and safe AI tools, which usually involve training on supervised datasets. Popular algorithms such as Direct Preference Optimization (DPO) rely…
LLM alignment ensures that large language models behave safely and effectively by aligning their outputs with human values, goals, and intentions. Aligning LLMs employ huge amounts of data, computation, and time. Moreover, curating data…
Word alignment over parallel corpora has a wide variety of applications, including learning translation lexicons, cross-lingual transfer of language processing tools, and automatic evaluation or analysis of translation outputs. The great…
When drafting question posts for Stack Overflow, developers may not accurately summarize the core problems in the question titles, which can cause these questions to not get timely help. Therefore, improving the quality of question titles…
Recent advancements in AI have sparked a trend in constructing large, generalist language models that handle a multitude of tasks, including many code-related ones. While these models are expensive to train and are often closed-source, they…
Context: Software developers often ask questions on Technical Q&A forums like Stack Overflow (SO) to seek solutions to their programming-related problems (e.g., errors and unexpected behavior of code). Problem: Many questions miss required…
Translating source code from one programming language to another is a critical, time-consuming task in modernizing legacy applications and codebases. Recent work in this space has drawn inspiration from the software naturalness hypothesis…
Near-duplicate text alignment is the task of identifying, among the texts in a corpus, all the subsequences (substrings) that are similar to a given query. Traditional approaches rely on seeding-extension-filtering heuristics, which lack…
We approach the important challenge of code autocompletion as an open-domain task, in which a sequence-to-sequence code generator model is enhanced with the ability to attend to reference code snippets supplied by a semantic code search…
Alignment is a crucial step to enhance the instruction-following and conversational abilities of language models. Despite many recent work proposing new algorithms, datasets, and training pipelines, there is a lack of comprehensive studies…