Related papers: CoaCor: Code Annotation for Code Retrieval with Re…
Reasoning models (RMs), language models (LMs) trained with reinforcement learning to produce long-form natural language reasoning, have been remarkably successful, but they still require large amounts of computation and data to train, and…
Retrieval-Augmented Code Generation (RACG) is a critical technique for enhancing code generation by retrieving relevant information. In this work, we conduct an in-depth analysis of code retrieval by systematically masking specific features…
Existing reinforcement learning strategies based on outcome supervision have proven effective in enhancing the performance of large language models(LLMs) for code generation. While reinforcement learning based on process supervision has…
When implementing unfamiliar programming tasks, developers commonly search code examples and learn usage patterns of APIs from the code examples or reuse them by copy-pasting and modifying. For providing high-quality code examples, previous…
We address contextualized code retrieval, the search for code snippets helpful to fill gaps in a partial input program. Our approach facilitates a large-scale self-supervised contrastive training by splitting source code randomly into…
Large language models (LLMs) have shown promising results for software engineering applications, but still struggle with code reasoning tasks such as vulnerability detection (VD). We introduce ConceptCoder, a fine-tuning method that…
There has been a recent surge of interest in automating software engineering tasks using deep learning. This paper addresses the problem of code generation, where the goal is to generate target code given source code in a different language…
The objective of image captioning models is to bridge the gap between the visual and linguistic modalities by generating natural language descriptions that accurately reflect the content of input images. In recent years, researchers have…
Automatically generating source code from natural language descriptions has been a growing field of research in recent years. However, current large-scale code generation models often encounter difficulties when selecting appropriate APIs…
Code intelligence is an emerging domain in software engineering, aiming to improve the effectiveness and efficiency of various code-related tasks. Recent research suggests that incorporating contextual information beyond the basic original…
In practice, rigorous reasoning is often a key driver of correct code, while Reinforcement Learning (RL) for code generation often neglects optimizing reasoning quality. Bringing process-level supervision into RL is appealing, but it faces…
Large Language Models have revolutionized code generation ability by converting natural language descriptions into executable code. However, generating complex code within real-world scenarios remains challenging due to intricate…
As an integral part of source code files, code comments help improve program readability and comprehension. However, developers sometimes do not comment on their program code adequately due to the incurred extra efforts, lack of relevant…
One common task of developing or maintaining software is searching the source code for information like specific method calls or write accesses to certain fields. This kind of information is required to correctly implement new features and…
Reinforcement Learning from Verifiable Rewards (RLVR) has driven recent progress in code large language models by leveraging execution-based feedback from unit tests, but its scalability is fundamentally constrained by the availability and…
In this paper, we propose the CodeRetriever model, which learns the function-level code semantic representations through large-scale code-text contrastive pre-training. We adopt two contrastive learning schemes in CodeRetriever: unimodal…
Large-scale, high-quality corpora are critical for advancing research in coreference resolution. However, existing datasets vary in their definition of coreferences and have been collected via complex and lengthy guidelines that are curated…
Reinforcement learning (RL) to improve code review comment generation requires handling unstructured outputs, making reinforcement learning (RL) feedback challenging. The two main RL approaches, namely RL with Verifiable Feedback (RLVR) and…
CodeLLMs have demonstrated remarkable advancements in software engineering tasks. However, while these models can generate functionally correct code, they often produce code that is inefficient in terms of runtime. This inefficiency is…
Code search is an important and well-studied task, but it usually means searching for code by a text query. We argue that using a code snippet (and possibly an error traceback) as a query while looking for bugfixing instructions and code…