Papers Code Completion
“Code Completion” 태그가 달린 논문 280편 · 필터 해제
MarsCode Agent: AI-native Automated Bug Fixing
Recent advances in large language models (LLMs) have shown significant potential to automate various software development tasks, including code completion, test generation, and bug fixing. However, the application of LLM…
Bug fixingCode CompletionDiversityFault localizationDataSculpt: Crafting Data Landscapes for Long-Context LLMs through Multi-Objective Partitioning
In recent years, Large Language Models (LLMs) have demonstrated significant improvements across a variety of tasks, one of which is the long-context capability. The key to improving long-context performance lies in effec…
Code CompletionCombinatorial OptimizationManagementReading Comprehension+3Revisiting VerilogEval: A Year of Improvements in Large-Language Models for Hardware Code Generation
The application of large-language models (LLMs) to digital hardware code generation is an emerging field, with most LLMs primarily trained on natural language and software code. Hardware code like Verilog constitutes a s…
Code CompletionCode GenerationIn-Context LearningPrompt EngineeringSecurity Attacks on LLM-based Code Completion Tools
The rapid development of large language models (LLMs) has significantly advanced code completion capabilities, giving rise to a new generation of LLM-based Code Completion Tools (LCCTs). Unlike general-purpose LLMs, thes…
Code CompletionRetrieval-augmented code completion for local projects using large language models
The use of large language models (LLMs) is becoming increasingly widespread among software developers. However, privacy and computational requirements are problematic with commercial solutions and the use of LLMs. In thi…
Code CompletionRAGRetrievalRetrieval-augmented GenerationRepoMasterEval: Evaluating Code Completion via Real-World Repositories
With the growing reliance on automated code completion tools in software development, the need for robust evaluation benchmarks has become critical. However, existing benchmarks focus more on code generation tasks in fun…
Code CompletionCode GenerationDescriptiveBlack-Box Adversarial Attacks on LLM-Based Code Completion
Modern code completion engines, powered by large language models (LLMs), assist millions of developers with their strong capabilities to generate functionally correct code. Due to this popularity, it is crucial to invest…
Code CompletionCode GenerationTaskEval: Assessing Difficulty of Code Generation Tasks for Large Language Models
Large Language Models (LLMs) excel in code-related tasks like code generation, but benchmark evaluations often overlook task characteristics, such as difficulty. Moreover, benchmarks are usually built using tasks describ…
BenchmarkingCode CompletionCode GenerationHumanEvalEvaluating Long Range Dependency Handling in Code Generation Models using Multi-Step Key Retrieval
As language models support larger and larger context sizes, evaluating their ability to make effective use of that context becomes increasingly important. We analyze the ability of several code generation models to handl…
8kCode CompletionCode GenerationRetrievalScaling Granite Code Models to 128K Context
This paper introduces long-context Granite code models that support effective context windows of up to 128K tokens. Our solution for scaling context length of Granite 3B/8B code models from 2K/4K to 128K consists of a li…
2k4kCode CompletionContinual Pretraining+1Curriculum Learning for Small Code Language Models
Code language models have emerged as useful tools for various programming tasks, yet they often struggle when it comes to complex ones. In this paper, we explore the potential of curriculum learning in enhancing the perf…
Code CompletionDecoderTPIA: Towards Target-specific Prompt Injection Attack against Code-oriented Large Language Models
Recently, code-oriented large language models (Code LLMs) have been widely and successfully exploited to simplify and facilitate programming. Unfortunately, a few pioneering works revealed that these Code LLMs are vulner…
Code CompletionJailbreak Attacks and Defenses Against Large Language Models: A Survey
Large Language Models (LLMs) have performed exceptionally in various text-generative tasks, including question answering, translation, code completion, etc. However, the over-assistance of LLMs has raised the challenge o…
Code CompletionQuestion AnsweringSafety AlignmentSurveyOn the Workflows and Smells of Leaderboard Operations (LBOps): An Exploratory Study of Foundation Model Leaderboards
Foundation models (FM), such as large language models (LLMs), which are large-scale machine learning (ML) models, have demonstrated remarkable adaptability in various downstream software engineering (SE) tasks, such as c…
Code CompletionHierarchical Context Pruning: Optimizing Real-World Code Completion with Repository-Level Pretrained Code LLMs
Some recently developed code large language models (Code LLMs) have been pre-trained on repository-level code data (Repo-Code LLMs), enabling these models to recognize repository structures and utilize cross-file informa…
Code CompletionLong Code Arena: a Set of Benchmarks for Long-Context Code Models
Nowadays, the fields of code and natural language processing are evolving rapidly. In particular, models become better at processing long context windows - supported context sizes have increased by orders of magnitude ov…
Code CompletionCode GenerationCodeGemma: Open Code Models Based on Gemma
This paper introduces CodeGemma, a collection of specialized open code models built on top of Gemma, capable of a variety of code and natural language generation tasks. We release three model variants. CodeGemma 7B pretr…
Code CompletionMathematical ReasoningNatural Language UnderstandingText GenerationMeasuring memorization in RLHF for code completion
Reinforcement learning with human feedback (RLHF) has become the dominant method to align large models to user preferences. Unlike fine-tuning, for which there are many studies regarding training data memorization, it is…
Code CompletionMemorizationreinforcement-learningReinforcement LearningVersiCode: Towards Version-controllable Code Generation
Large Language Models (LLMs) have made tremendous strides in code generation, but existing research fails to account for the dynamic nature of software development, marked by frequent library updates. This gap significan…
Code CompletionCode GenerationLanguage ModellingLarge Language ModelAn LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection
Large Language Models (LLMs) have transformed code completion tasks, providing context-based suggestions to boost developer productivity in software engineering. As users often fine-tune these models for specific applica…
Backdoor AttackCode CompletionVulnerability Detection