Papers Code Completion
“Code Completion” 태그가 달린 논문 280편 · 필터 해제
Breaking the Silence: the Threats of Using LLMs in Software Engineering
Large Language Models (LLMs) have gained considerable traction within the Software Engineering (SE) community, impacting various SE tasks from code completion to test generation, from program repair to code summarization…
Code CompletionCode SummarizationLanguage ModelingLanguage Modelling+1INSPECT: Intrinsic and Systematic Probing Evaluation for Code Transformers
Pre-trained models of source code have recently been successfully applied to a wide variety of Software Engineering tasks; they have also seen some practical adoption in practice, e.g. for code completion. Yet, we still …
Code CompletionDiagnosticLanguage ModellingInterpretability Illusions in the Generalization of Simplified Models
A common method to study deep learning systems is to use simplified model representations--for example, using singular value decomposition to visualize the model's hidden states in a lower dimensional space. This approac…
Code CompletionDimensionality ReductionSystematic GeneralizationGenCodeSearchNet: A Benchmark Test Suite for Evaluating Generalization in Programming Language Understanding
Language models can serve as a valuable tool for software developers to increase productivity. Large generative models can be used for code generation and code completion, while smaller encoder-only models are capable of…
Code CompletionCode GenerationCode SearchDiversityPast as a Guide: Leveraging Retrospective Learning for Python Code Completion
This work presents Past as a Guide (PaG), a simple approach for Large Language Models (LLMs) to improve the coding capabilities by integrating the past history with interactive and iterative code refinements. To be speci…
Code CompletionHumanEvalIdentifying and Mitigating Vulnerabilities in LLM-Integrated Applications
Large language models (LLMs) are increasingly deployed as the service backend for LLM-integrated applications such as code completion and AI-powered search. LLM-integrated applications serve as middleware to refine users…
Code CompletionAttention Alignment and Flexible Positional Embeddings Improve Transformer Length Extrapolation
An ideal length-extrapolatable Transformer language model can handle sequences longer than the training length without any fine-tuning. Such long-context utilization capability relies heavily on a flexible positional emb…
Code CompletionLanguage ModelingLanguage ModellingQuestion Answering+1CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion
Code completion models have made significant progress in recent years, yet current popular evaluation datasets, such as HumanEval and MBPP, predominantly focus on code completion tasks within a single file. This over-sim…
Code CompletionHumanEvalmbppLongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression
In long context scenarios, large language models (LLMs) face three main challenges: higher computational cost, performance reduction, and position bias. Research indicates that LLM performance hinges on the density and p…
Code CompletionFew-Shot LearningPositionCritique Ability of Large Language Models
Critical thinking is essential for rational decision-making and problem-solving. This skill hinges on the ability to provide precise and reasoned critiques and is a hallmark of human intelligence. In the era of large lan…
Code CompletionDecision MakingMathNatural Language Queries+1Ada-Instruct: Adapting Instruction Generators for Complex Reasoning
Instructions augmentation is a crucial step for unleashing the full potential of large language models (LLMs) in downstream tasks. Existing Self-Instruct methods primarily simulate new instructions from a few initial ins…
Code CompletionIn-Context LearningMathematical ReasoningBAMBOO: A Comprehensive Benchmark for Evaluating Long Text Modeling Capacities of Large Language Models
Large language models (LLMs) have achieved dramatic proficiency over NLP tasks with normal length. Recently, multiple studies have committed to extending the context length and enhancing the long text modeling capabiliti…
Code CompletionHallucinationLanguage ModelingLanguage Modelling+1LayoutNUWA: Revealing the Hidden Layout Expertise of Large Language Models
Graphic layout generation, a growing research field, plays a significant role in user engagement and information perception. Existing methods primarily treat layout generation as a numerical optimization task, focusing o…
Code CompletionCode GenerationLayout GenerationLaminar: A New Serverless Stream-based Framework with Semantic Code Search and Code Completion
This paper introduces Laminar, a novel serverless framework based on dispel4py, a parallel stream-based dataflow library. Laminar efficiently manages streaming workflows and components through a dedicated registry, offer…
Code CompletionCode SearchCode SummarizationCodeMark: Imperceptible Watermarking for Code Datasets against Neural Code Completion Models
Code datasets are of immense value for training neural-network-based code completion models, where companies or organizations have made substantial investments to establish and process these datasets. Unluckily, these da…
Code CompletionSpecificityLongBench: A Bilingual, Multitask Benchmark for Long Context Understanding
Although large language models (LLMs) demonstrate impressive performance for many language tasks, most of them can only handle texts a few thousand tokens long, limiting their applications on longer sequence inputs, such…
16kCode CompletionFew-Shot LearningLong-Context UnderstandingIdentifying and Mitigating the Security Risks of Generative AI
Every major technical invention resurfaces the dual-use dilemma -- the new technology has the potential to be used for good as well as for harm. Generative AI (GenAI) techniques, such as large language models (LLMs) and …
Code CompletionImage GenerationIn-Context LearningText to Image Generation+1Benchmarking Causal Study to Interpret Large Language Models for Source Code
One of the most common solutions adopted by software researchers to address code generation is by training Large Language Models (LLMs) on massive amounts of source code. Although a number of studies have shown that LLMs…
BenchmarkingCausal InferenceCode CompletionCode Generation+2Scope is all you need: Transforming LLMs for HPC Code
With easier access to powerful compute resources, there is a growing trend in the field of AI for software development to develop larger and larger language models (LLMs) to address a variety of programming tasks. Even L…
AllCode CompletionSecureFalcon: Are We There Yet in Automated Software Vulnerability Detection with LLMs?
Software vulnerabilities can cause numerous problems, including crashes, data loss, and security breaches. These issues greatly compromise quality and can negatively impact the market adoption of software applications an…
Binary ClassificationBug fixingC++ codeCode Completion+3