SE Tasks
Table of contents
- Code Completion
- Code search
- Code summarization
- Program synthesis
- Program Repair
- Code clone detection
- Bug report analysis
- Code Review
- Test generation
- Vulnerability detection
- Code Generation
Code Completion
- A systematic evaluation of large language models of code, 2022;
- An empirical study on the usage of transformer models for code completion, 2021, link
- Automatic detection and analysis of technical debts in peer-review documentation of r packages, 2022, link
- CCTest: Testing and repairing code completion systems, 2023, link
- CodeFill: Multi-token code completion by jointly learning from structure and naming sequences, 2022, link
- Evaluating and improving transformers pre-trained on ASTs for code completion, 2023, link
- Examining zero-shot vulnerability repair with large language models, 2022, link
- From Copilot to Pilot: Towards AI supported software development, 2023, link
- Making the most of small Software Engineering datasets with modern machine learning, 2022, link
- Multi-task learning based pre-trained language model for code completion, 2020, link
- Natural Language Generation and Understanding of Big Code for AI-Assisted Programming: A Review, 2023;
- Piloting Copilot and Codex: Hot temperature, cold prompts, or black magic?, 2023, link
- RepoBench: Benchmarking repository-level code auto-completion systems, 2023, link
- Toward less hidden cost of code completion with acceptance and ranking models, 2021, link
- An Empirical Study on Code Comment Completion, 2021, link
- Large Language Models are Few-shot Summarizers: Multi-intent Comment Generation via In-context Learning, 2023, link
Code search
- Cross-Modal Contrastive Learning for Code Search, 2022, link
- Do Pre-trained Language Models Indeed Understand Software Engineering Tasks?, 2022, link
- Generation-Augmented Query Expansion for Code Retrieval, 2022, link
- On Contrastive Learning of Semantic Similarity for Code-to-Code Search, 2023, link
- On the Effectiveness of Transfer Learning for Code Search, 2023, link
Code summarization
- Assemble Foundation Models for Automatic Code Summarization, 2022, link
- Constructing Effective In-Context Demonstration for Code Intelligence Tasks: An Empirical Study, 2023, link
- Exploring Distributional Shifts in Large Language Models for Code Analysis, 2023, link
- Extending Source Code Pre-trained Language Models to Summarise Decompiled Binaries, 2023, link
- Improving Few-shot Prompts with Relevant Static Analysis Products, 2023, link
- Multilingual Adapter-based Knowledge Aggregation on Code Summarization for Low-Resource Languages, 2023
- On the Transferability of Pre-trained Language Models for Low-Resource Programming Languages, 2022, link
- Studying the Usage of Text-to-Text Transfer Transformer to Support Code-Related Tasks, 2021, link
- Using Transfer Learning for Code-Related Tasks, 2023, link
Program synthesis
- Evaluating ChatGPT and GPT-4 for Visual Programming, 2023
- Exploring the Robustness of Large Language Models for Solving Programming Problems, 2023
- Jigsaw: Large Language Models Meet Program Synthesis, 2022, link
- Less is More: Summary of Long Instructions is Better for Program Synthesis, 2022
- Natural Language Commanding via Program Synthesis, 2023, link
Program Repair
- Toward less hidden cost of code completion with acceptance and ranking models, 2021, link
- A Chain of AI-based Solutions for Resolving FQNs and Fixing Syntax Errors in Partial Code, 2023
- a new era in software security: towards self-healing software via large language models and formal verification, 2023, link
- a prompt pattern catalog to enhance prompt engineering with chatgpt, 2023, link
- a study on prompt design, advantages and limitations of chatgpt for deep learning program repair, 2023, link
- Addressing Compiler Errors: Stack Overflow or Large Language Models?, 2023
- an analysis of the automatic bug fixing performance of chatgpt, 2023, link
- automated repair of programs from large language models, 2023, link
- boosting automated patch correctness prediction via pre-trained language model, 2023, link
- circle: continual repair across programming languages, 2022, link
- constructing effective in-context demonstration for code intelligence tasks: an empirical study, 2023, link
- conversational automated program repair, 2023, link
- Enhancing Automated Program Repair through Fine-tuning and Prompt Engineering, 2023
- evaluating representation learning of code changes for predicting patch correctness in program repair, 2020, link
- how effective are neural networks for fixing security vulnerabilities, 2023, link
- inferfix: end-to-end program repair with llms, 2023, link
- invalidator: automated patch correctness assessment via semantic and syntactic reasoning, 2023, link
- is chatgpt the ultimate programming assistant – how far is it?, 2023, link
- keep the conversation going: fixing 162 out of 337 bugs for $0.42 each using chatgpt, 2023, link
- neural program repair with program dependence analysis and effective filter mechanism, 2023, link
- practical program repair in the era of large pre-trained language models, 2022, link
- the best of both worlds: combining learned embeddings with engineered features for accurate prediction of correct patches, 2023, link
- towards javascript program repair with generative pre-trained transformer (gpt-2), 2022, link
- using transfer learning for code-related tasks, 2023
Code clone detection
- an exploratory study on code attention in bert, 2022, link
- Towards Understanding the Capability of Large Language Models on Code Clone Detection: A Survey, 2023
- Utilization of Pre-trained Language Model for Adapter-based Knowledge Transfer in Software Engineering, 2023
Bug report analysis
- fast changeset-based bug localization with bert, 2022, link
- Few-shot learning for sentence pair classification and its applications in software engineering, 2023
- large language models are few-shot testers: exploring llm-based general bug reproduction, 2022, link
Code Review
- A Multi-Step Learning Approach to Assist Code Review, 2023
- aspect-based api review classification: how far can pre-trained transformer model go?, 2022, link
- auger: automatically generating review comments with pre-training models, 2022, link
- Automated Summarization of Stack Overflow Posts, 2023, link
- coditt5: pretraining for source code and natural language editing, 2022, link
- using pre-trained models to boost code review automation, 2022, link
Test generation
- adaptive test generation using a large language model, 2023, link
- algo: synthesizing algorithmic programs with generated oracle verifiers, 2023, link
- Can Large Language Models Write Good Property-Based Tests?, 2023
- chatunitest: a chatgpt-based automated unit test generation tool, 2023, link
- exploring the effectiveness of large language models in generating unit tests, 2023, link
- no more manual tests? evaluating and improving chatgpt for unit test generation, 2023, link
Vulnerability detection
- csgvd: a deep learning approach combining sequence and graph embedding for source code vulnerability detection, 2023, link
- Detecting Phishing Sites Using ChatGPT, 2023
- diversevul: a new vulnerable source code dataset for deep learning-based vulnerability detection, 2023, link
- low-level source code vulnerability detection using advanced BERT language model, 2022, link
- transformer-based language models for software vulnerability detection, 2022, link
- transformer-based vulnerability detection in code at edittime: zero-shot, few-shot, or fine-tuning?, 2023, link
- When GPT Meets Program Analysis: Towards Intelligent Detection of Smart Contract Logic Vulnerabilities in GPTScan, 2023
Code Generation
- A Lightweight Framework for High-Quality Code Generation, 2023
- A Syntax-Guided Multi-Task Learning Approach for Turducken-Style Code Generation, 2023, link
- A Systematic Study and Comprehensive Evaluation of ChatGPT on Benchmark Datasets, 2023
- AI for Low-Code for AI, 2023, link
- Aligning Offline Metrics and Human Judgments of Value of AI-Pair Programmers, 2022, link
- An Extensive Study on Pre-trained Models for Program Understanding and Generation, 2022, link
- ANPL: Compiling Natural Programs with Interactive Decomposition, 2023, link
- Capturing Failures of Large Language Models via Human Cognitive Biases, 2022, link
- CERT: Continual Pre-training on Sketches for Library-Oriented Code Generation, 2022, link
- ClassEval: A Manually-Crafted Benchmark for Evaluating LLMs on Class-level Code Generation, 2023
- Code Generation Tools (Almost) for Free? A Study of Few-shot, Pre-trained Language Models on Code, 2022, link
- CodeCompose: A Large-scale Industrial Deployment of AI-assisted Code Authoring, 2023, link
- CodeGeex: A Pre-trained Model for Code Generation with Multilingual Evaluations on Humaneval-X, 2023, link
- CodeIE: Large Code Generation Models Are Better Few-shot Information Extractors, 2023, link
- CodeEval: A Benchmark of Pragmatic Code Generation with Generative Pre-trained Models, 2023, link
- Comparing Software Developers with ChatGPT: An Empirical Investigation, 2023, link
- Copilot for Xcode: Exploring AI-Assisted Programming by Prompting Cloud-based Large Language Models, 2023
- Demystifying GPT Self-Repair for Code Generation, 2023
- DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation, 2022, link
- Enabling Programming Thinking in Large Language Models Toward Code Generation, 2023
- Evaluating AIGC Detectors on Code Content, 2023, link
- Evaluating Large Language Models Trained on Code, 2021, link
- Evaluating the Code Quality of AI-Assisted Code Generation Tools: An Empirical Study on GitHub Copilot, Amazon CodeWhisperer, and ChatGPT, 2023, link
- Extending the Frontier of ChatGPT: Code Generation and Debugging, 2023
- GRACE: Generation using Associated Code Edits, 2023, link
- Improving ChatGPT Prompt for Code Generation, 2023, link
- Improving Code Generation by Training with Natural Language Feedback, 2023, link
- Interactive Code Generation via Test-Driven User-Intent Formalization, 2022, link
- Is Model Attention Aligned with Human Attention? An Empirical Study on Large Language Models for Code Generation, 2023, link
- Is this Snippet Written by ChatGPT? An Empirical Study with, 2023