Papers Text-to-Code Generation
“Text-to-Code Generation” 태그가 달린 논문 23편 · 필터 해제
CS-Guard: Benchmarking LLM Guardrails for Code Generation Security
Large language models (LLMs) have been ex- ploited to generate malware, but the effective- ness of guardrails for code generation secu- rity remains unclear. We introduce CS-Guard, the first benchmark to systematically e…
Text-to-Code GenerationCode TranslationCode CompletionExploring different approaches to customize language models for domain-specific text-to-code generation
Large language models (LLMs) have demonstrated strong capabilities in generating executable code from natural language descriptions. However, general-purpose models often struggle in specialized programming contexts wher…
parameter-efficient fine-tuningText-to-Code GenerationFew-Shot LearningCangjieBench: Benchmarking LLMs on a Low-Resource General-Purpose Programming Language
Large Language Models excel in high-resource programming languages but struggle with low-resource ones. Existing research related to low-resource programming languages primarily focuses on Domain-Specific Languages (DSLs…
Text-to-Code GenerationCode TranslationBridging the Gap Between Open-Source and Proprietary LLMs in Table QA
This paper presents a system developed for SemEval 2025 Task 8: Question Answering (QA) over tabular data. Our approach integrates several key components: text-to-SQL and text-to-code generation modules, a self-correctio…
Code GenerationLanguage ModelingLanguage ModellingLarge Language Model+6Aligning Crowd-sourced Human Feedback for Reinforcement Learning on Code Generation by Large Language Models
This paper studies how AI-assisted programming and large language models (LLM) improve software developers' ability via AI tools (LLM agents) like Github Copilot and Amazon CodeWhisperer, while integrating human feedback…
Bayesian OptimizationCode GenerationLanguage ModelingLanguage Modelling+2Planning-Driven Programming: A Large Language Model Programming Workflow
The strong performance of large language models (LLMs) raises extensive discussion on their application to code generation. Recent research suggests continuous program refinements through visible tests to improve code ge…
Code GenerationHumanEvalLanguage ModelingLanguage Modelling+4SparsePO: Controlling Preference Alignment of LLMs via Sparse Token Masks
Preference Optimization (PO) has proven an effective step for aligning language models to human-desired behaviors. Current variants, following the offline Direct Preference Optimization objective, have focused on a stric…
Code GenerationText SummarizationText-to-Code GenerationReranking Laws for Language Generation: A Communication-Theoretic Perspective
To ensure large language models (LLMs) are used safely, one must reduce their propensity to hallucinate or to generate unacceptable answers. A simple and often used strategy is to first let the LLM generate multiple hypo…
Code GenerationMachine TranslationRerankingText Generation+1Can OpenSource beat ChatGPT? -- A Comparative Study of Large Language Models for Text-to-Code Generation
In recent years, large language models (LLMs) have emerged as powerful tools with potential applications in various fields, including software engineering. Within the scope of this research, we evaluate five different st…
Code GenerationText-to-Code GenerationGenerating Unseen Code Tests In Infinitum
Large Language Models (LLMs) are used for many tasks, including those related to coding. An important aspect of being able to utilize LLMs is the ability to assess their fitness for specific usages. The common practice i…
Code GenerationregressionText-to-Code GenerationInverseCoder: Self-improving Instruction-Tuned Code LLMs with Inverse-Instruct
Recent advancements in open-source code large language models (LLMs) have been driven by fine-tuning on the data generated from powerful closed-source LLMs, which are expensive to obtain. This paper explores whether it i…
Code GenerationCode SummarizationData AugmentationHumanEval+2Can Large Language Models Solve Robot Routing?
Routing problems are common in mobile robotics, encompassing tasks such as inspection, surveillance, and coverage. Depending on the objective and constraints, these problems often reduce to variants of the Traveling Sale…
Code GenerationText-to-Code GenerationTraveling Salesman ProblemText-to-Code Generation with Modality-relative Pre-training
Large pre-trained language models have recently been expanded and applied to programming language tasks with great success, often through further pre-training of a strictly-natural language model--where training sequence…
Code GenerationLanguage ModelingLanguage ModellingText-to-Code Generation+1Magicoder: Empowering Code Generation with OSS-Instruct
We introduce Magicoder, a series of fully open-source (code, weights, and data) Large Language Models (LLMs) for code that significantly closes the gap with top code models while having no more than 7B parameters. Magico…
Code GenerationHumanEvalText-to-Code GenerationFine-Tuning Large Language Models for Answering Programming Questions with Code Snippets
We study the ability of pretrained large language models (LLM) to answer questions from online question answering fora such as Stack Overflow. We consider question-answer pairs where the main part of the answer consists …
Code GenerationLanguage ModellingProgram SynthesisPrompt Engineering+2Guiding Language Models of Code with Global Context using Monitors
Language models of code (LMs) work well when the surrounding code provides sufficient context. This is not true when it becomes necessary to use types, functionality or APIs defined elsewhere in the repository or a linke…
Code CompletionCode GenerationCode RepairCode Translation+1Code Execution with Pre-trained Language Models
Code execution is a fundamental aspect of programming language semantics that reflects the exact behavior of the code. However, most pre-trained models for code intelligence ignore the execution trace and only rely on so…
Code GenerationCode SearchData AugmentationText-to-Code GenerationC3PO: A Lightweight Copying Mechanism for Translating Pseudocode to Code
Writing computer programs is a skill that remains inaccessible to most due to the barrier of programming language (PL) syntax. While large language models (LLMs) have been proposed to translate natural language pseudocod…
Code TranslationText-to-Code GenerationPanGu-Coder: Program Synthesis with Function-Level Language Modeling
We present PanGu-Coder, a pretrained decoder-only language model adopting the PanGu-Alpha architecture for text-to-code generation, i.e. the synthesis of programming language solutions given a natural language problem de…
Code GenerationDecoderLanguage ModelingLanguage Modelling+2StructCoder: Structure-Aware Transformer for Code Generation
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 …
Code GenerationCode TranslationDecoderText-to-Code Generation