Related papers: Completion by Comprehension: Guiding Code Generati…

Retrieval-Augmented Generation (RAG) has emerged as a promising paradigm for improving the timeliness of knowledge updates and the factual accuracy of large language models. However, incorporating a large volume of retrieved documents…

Iterative Retrieval-Augmented Generation (iRAG) has emerged as a powerful paradigm for answering complex multi-hop questions by progressively retrieving and reasoning over external documents. However, current systems predominantly operate…

Document understanding is critical for applications from financial analysis to scientific discovery. Current approaches, whether OCR-based pipelines feeding Large Language Models (LLMs) or native Multimodal LLMs (MLLMs), face key…

Retrieval-augmented generation (RAG) systems have predominantly focused on text-based retrieval, limiting their effectiveness in handling visually-rich documents that encompass text, images, tables, and charts. To bridge this gap, we…

Repository-level code generation remains challenging due to complex code dependencies and the limitations of large language models (LLMs) in processing long contexts. While retrieval-augmented generation (RAG) frameworks are widely adopted,…

Code completion aims to enhance programming productivity by predicting potential code based on the current programming context. Recently, pretrained language models (LMs) have become prominent in this field. Various approaches have been…

To accelerate software development, much research has been performed to help people understand and reuse the huge amount of available code resources. Two important tasks have been widely studied: code retrieval, which aims to retrieve code…

Transformer-based pre-trained models have recently achieved great results in solving many software engineering tasks including automatic code completion which is a staple in a developer's toolkit. While many have striven to improve the…

Retrieval-Augmented Generation (RAG) allows overcoming the limited knowledge of LLMs by extending the input with external information. As a consequence, the contextual inputs to the model become much longer which slows down decoding time…

Recent advancements in Large Language Models (LLMs) have transformed code generation from natural language queries. However, despite their extensive knowledge and ability to produce high-quality code, LLMs often struggle with contextual…

Domain-specific QA systems require not just generative fluency but high factual accuracy grounded in structured expert knowledge. While recent Retrieval-Augmented Generation (RAG) frameworks improve context recall, they struggle with…

Despite Retrieval-Augmented Generation improving code completion, traditional retrieval methods struggle with information redundancy and a lack of diversity within limited context windows. To solve this, we propose a resource-optimized…

Context plays an important role in the quality of code completion, as Large Language Models (LLMs) require sufficient and relevant information to assist developers in code generation tasks. However, composing a relevant context for code…

Retrieval-augmented generation has emerged as one of the most effective approaches for code completion enhancement, especially when repository-level context is important. However, adding this extra retrieved context significantly increases…

Combinatorial optimization (CO) problems, central to operation research and theoretical computer science, present significant computational challenges due to their NP-hard nature. While large language models (LLMs) have emerged as promising…

Large language models that enhance software development tasks, such as code generation, code completion, and code question answering (QA), have been extensively studied in both academia and the industry. The models are integrated into…

Retrieval-Augmented Generation (RAG) has emerged as a fundamental paradigm for expanding Large Language Models beyond their static training limitations. However, a critical misalignment exists between current RAG capabilities and real-world…

Repository-level code generation has attracted growing attention in recent years. Unlike function-level code generation, it requires the model to understand the entire repository, reasoning over complex dependencies across functions,…

Writing code requires significant time and effort in software development. To automate this process, researchers have made substantial progress for code generation. Recently, large language models (LLMs) have demonstrated remarkable…

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…