Papers Code Completion
“Code Completion” 태그가 달린 논문 280편 · 필터 해제
Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle Tasks
We introduce Syntax-Aware Fill-In-the-Middle (SAFIM), a new benchmark for evaluating Large Language Models (LLMs) on the code Fill-in-the-Middle (FIM) task. This benchmark focuses on syntax-aware completions of program s…
Code CompletionIRCoder: Intermediate Representations Make Language Models Robust Multilingual Code Generators
Code understanding and generation have fast become some of the most popular applications of language models (LMs). Nonetheless, research on multilingual aspects of Code-LMs (i.e., LMs for code generation) such as cross-l…
Code CompletionCode GenerationCross-Lingual TransferData Augmentation+2StarCoder 2 and The Stack v2: The Next Generation
The BigCode project, an open-scientific collaboration focused on the responsible development of Large Language Models for Code (Code LLMs), introduces StarCoder2. In partnership with Software Heritage (SWH), we build The…
Code CompletionCode GenerationMathInsights from the Usage of the Ansible Lightspeed Code Completion Service
The availability of Large Language Models (LLMs) which can generate code, has made it possible to create tools that improve developer productivity. Integrated development environments or IDEs which developers use to writ…
Code CompletionCode GenerationCodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models
Adversarial misuse, particularly through `jailbreaking' that circumvents a model's safety and ethical protocols, poses a significant challenge for Large Language Models (LLMs). This paper delves into the mechanisms behin…
Code CompletionResponse GenerationLanguage Models for Code Completion: A Practical Evaluation
Transformer-based language models for automatic code completion have shown great promise so far, yet the evaluation of these models rarely uses real data. This study provides both quantitative and qualitative assessments…
Code CompletionvalidREPOFUSE: Repository-Level Code Completion with Fused Dual Context
The success of language models in code assistance has spurred the proposal of repository-level code completion as a means to enhance prediction accuracy, utilizing the context from the entire codebase. However, this ampl…
Code CompletionContext Composing for Full Line Code Completion
Code Completion is one of the most used Integrated Development Environment (IDE) features, which affects the everyday life of a software developer. Modern code completion approaches moved from the composition of several …
Code CompletionDo Large Code Models Understand Programming Concepts? Counterfactual Analysis for Code Predicates
Large Language Models' success on text generation has also made them better at code generation and coding tasks. While a lot of work has demonstrated their remarkable performance on tasks such as code completion and edit…
Code CompletionCode GenerationcounterfactualText GenerationNeural Models for Source Code Synthesis and Completion
Natural language (NL) to code suggestion systems assist developers in Integrated Development Environments (IDEs) by translating NL utterances into compilable code snippet. The current approaches mainly involve hard-coded…
Code CompletionData AugmentationLanguage ModellingSemantic ParsingEnhancing LLM-Based Coding Tools through Native Integration of IDE-Derived Static Context
Large Language Models (LLMs) have achieved remarkable success in code completion, as evidenced by their essential roles in developing code assistant services such as Copilot. Being trained on in-file contexts, current LL…
Code CompletionBreak the Sequential Dependency of LLM Inference Using Lookahead Decoding
Autoregressive decoding of large language models (LLMs) is memory bandwidth bounded, resulting in high latency and significant wastes of the parallel processing power of modern accelerators. Existing methods for accelera…
Code CompletionEffiBench: Benchmarking the Efficiency of Automatically Generated Code
Code generation models have increasingly become integral to aiding software development. Although current research has thoroughly examined the correctness of the code produced by code generation models, a vital aspect th…
BenchmarkingCode CompletionCode GenerationCode TranslationStepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback
The advancement of large language models (LLMs) has significantly propelled the field of code generation. Previous work integrated reinforcement learning (RL) with compiler feedback for exploring the output space of LLMs…
Code CompletionCode Generationreinforcement-learningReinforcement Learning+1OMPGPT: A Generative Pre-trained Transformer Model for OpenMP
Large language models (LLMs)such as ChatGPT have significantly advanced the field of Natural Language Processing (NLP). This trend led to the development of code-based large language models such as StarCoder, WizardCoder…
Code CompletionCode GenerationComment GenerationComputational Efficiency+1Can Large Language Models Write Parallel Code?
Large language models are increasingly becoming a popular tool for software development. Their ability to model and generate source code has been demonstrated in a variety of contexts, including code completion, summariz…
Code CompletionCode GenerationLanguage ModelingLanguage Modelling+1LangBridge: Multilingual Reasoning Without Multilingual Supervision
We introduce LangBridge, a zero-shot approach to adapt language models for multilingual reasoning tasks without multilingual supervision. LangBridge operates by bridging two models, each specialized in different aspects:…
Code CompletionLogical ReasoningMathematical ReasoningWhen Neural Code Completion Models Size up the Situation: Attaining Cheaper and Faster Completion through Dynamic Model Inference
Leveraging recent advancements in large language models, modern neural code completion models have demonstrated the capability to generate highly accurate code suggestions. However, their massive size poses challenges in…
Code CompletionDecision MakingTraces of Memorisation in Large Language Models for Code
Large language models have gained significant popularity because of their ability to generate human-like text and potential applications in various fields, such as Software Engineering. Large language models for code are…
Code CompletionA Review of Repository Level Prompting for LLMs
As coding challenges become more complex, recent advancements in Large Language Models (LLMs) have led to notable successes, such as achieving a 94.6\% solve rate on the HumanEval benchmark. Concurrently, there is an inc…
Code CompletionCode GenerationHumanEvalRetrieval