gai4se / llm4se Goto Github PK

https://arxiv.org/pdf/2305.07922.pdf

Survey paper: A Systematic Evaluation of Large Language Models of Code

Codex, GPT-J, GPT-Neo, GPT-NeoX-20B, and Code-Parrot

• vicuna
• alpaca
• llama

Would you add the following papers:

1. Using Large Language Models to Generate JUnit Tests: An Empirical Study - EASE'2024
2. Understanding Regular Expression Denial of Service (ReDoS): Insights from LLM-Generated Regexes and Developer Forums - ICPC'2024
3. Re(gEx|DoS)Eval: Evaluating Generated Regular Expressions and their Proneness to DoS Attacks - ICSE-NIER'2024

such as codexglue

Survey paper: Deep Learning Meets Software Engineering: A Survey on Pre-Trained Models of Source Code

• SCELMo
• CodeDisen
• CuBERT
• C-BERT
• JavaBERT
• CugLM
• CodeBERT
• OSCAR
• GraphCodeBERT
• SynCoBERT
• GPT-C
• DOBF
• DeepDebug
• T5-learning
• PLBART
• CoTexT
• ProphetNet-Code
• CodeT5
• TreeBERT
• SPT-Code

link with paper index

@thanhlecongg maybe u can help on this when ur free.

Paper #6
{
"title": "Using a Nearest-Neighbour, BERT-Based Approach for Scalable Clone Detection.",
"url": "https://doi.org/10.1109/ICSME55016.2022.00080",
"venue_name": "IEEE International Conference on Software Maintenance and Evolution",
"venue_type": "conf",
"year": 2022
}

Paper #7
{
"title": "Sentiment Analysis for Software Engineering: How Far Can Pre-trained Transformer Models Go?",
"url": "https://doi.org/10.1109/ICSME46990.2020.00017",
"venue_name": "IEEE International Conference on Software Maintenance and Evolution",
"venue_type": "conf",
"year": 2020
}

Paper #8
{
"title": "Achieving Reliable Sentiment Analysis in the Software Engineering Domain using BERT.",
"url": "https://doi.org/10.1109/ICSME46990.2020.00025",
"venue_name": "IEEE International Conference on Software Maintenance and Evolution",
"venue_type": "conf",
"year": 2020
}

Paper #9
{
"title": "A Transferable Time Series Forecasting Service Using Deep Transformer Model for Online Systems.",
"url": "https://doi.org/10.1145/3551349.3560414",
"venue_name": "IEEE/ACM International Conference on Automated Software Engineering",
"venue_type": "conf",
"year": 2022
}

Paper #10
{
"title": "PRCBERT: Prompt Learning for Requirement Classification using BERT-based Pretrained Language Models.",
"url": "https://doi.org/10.1145/3551349.3560417",
"venue_name": "IEEE/ACM International Conference on Automated Software Engineering",
"venue_type": "conf",
"year": 2022
}

Paper #11
{
"title": "A transformer-based IDE plugin for vulnerability detection.",
"url": "https://doi.org/10.1145/3551349.3559534",
"venue_name": "IEEE/ACM International Conference on Automated Software Engineering",
"venue_type": "conf",
"year": 2022
}

Paper #12
{
"title": "LineVul: A Transformer-based Line-Level Vulnerability Prediction.",
"url": "https://doi.org/10.1145/3524842.3528452",
"venue_name": "IEEE Working Conference on Mining Software Repositories",
"venue_type": "conf",
"year": 2022
}

Paper #13
{
"title": "An Empirical Study on the Usage of BERT Models for Code Completion.",
"url": "https://doi.org/10.1109/MSR52588.2021.00024",
"venue_name": "IEEE Working Conference on Mining Software Repositories",
"venue_type": "conf",
"year": 2021
}

Paper #14
{
"title": "Applying CodeBERT for Automated Program Repair of Java Simple Bugs.",
"url": "https://doi.org/10.1109/MSR52588.2021.00063",
"venue_name": "IEEE Working Conference on Mining Software Repositories",
"venue_type": "conf",
"year": 2021
}

Paper #15
{
"title": "AutoPruner: transformer-based call graph pruning.",
"url": "https://doi.org/10.1145/3540250.3549175",
"venue_name": "The ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering",
"venue_type": "conf",
"year": 2022
}

Paper #16
{
"title": "Program merge conflict resolution via neural transformers.",
"url": "https://doi.org/10.1145/3540250.3549163",
"venue_name": "The ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering",
"venue_type": "conf",
"year": 2022
}

Paper #17
{
"title": "Empirical study of transformers for source code.",
"url": "https://doi.org/10.1145/3468264.3468611",
"venue_name": "The ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering",
"venue_type": "conf",
"year": 2021
}

Paper #18
{
"title": "Fair preprocessing: towards understanding compositional fairness of data transformers in machine learning pipeline.",
"url": "https://doi.org/10.1145/3468264.3468536",
"venue_name": "The ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering",
"venue_type": "conf",
"year": 2021
}

Paper #19
{
"title": "IntelliCode compose: code generation using transformer.",
"url": "https://doi.org/10.1145/3368089.3417058",
"venue_name": "The ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering",
"venue_type": "conf",
"year": 2020
}

Paper #20
{
"title": "Source Code Summarization with Structural Relative Position Guided Transformer.",
"url": "https://doi.org/10.1109/SANER53432.2022.00013",
"venue_name": "IEEE International Conference on Software Analysis, Evolution, and Reengineering",
"venue_type": "conf",
"year": 2022
}

Paper #21
{
"title": "DualSC: Automatic Generation and Summarization of Shellcode via Transformer and Dual Learning.",
"url": "https://doi.org/10.1109/SANER53432.2022.00052",
"venue_name": "IEEE International Conference on Software Analysis, Evolution, and Reengineering",
"venue_type": "conf",
"year": 2022
}

Paper #22
{
"title": "Aspect-Based API Review Classification: How Far Can Pre-Trained Transformer Model Go?",
"url": "https://doi.org/10.1109/SANER53432.2022.00054",
"venue_name": "IEEE International Conference on Software Analysis, Evolution, and Reengineering",
"venue_type": "conf",
"year": 2022
}

Paper #23
{
"title": "SOTitle: A Transformer-based Post Title Generation Approach for Stack Overflow.",
"url": "https://doi.org/10.1109/SANER53432.2022.00075",
"venue_name": "IEEE International Conference on Software Analysis, Evolution, and Reengineering",
"venue_type": "conf",
"year": 2022
}

Paper #24
{
"title": "jTrans: jump-aware transformer for binary code similarity detection.",
"url": "https://doi.org/10.1145/3533767.3534367",
"venue_name": "International Symposium on Software Testing and Analysis",
"venue_type": "conf",
"year": 2022
}

counts: 25
venue_stats:
{
"IEEE Transactions on Software Engineering": 1,
"International Conference on Software Engineering": 5,
"IEEE International Conference on Software Maintenance and Evolution": 3,
"IEEE/ACM International Conference on Automated Software Engineering": 3,
"IEEE Working Conference on Mining Software Repositories": 3,
"The ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering": 5,
"IEEE International Conference on Software Analysis, Evolution, and Reengineering": 4,
"International Symposium on Software Testing and Analysis": 1
}

year_stats:
{
"2020": 3,
"2021": 8,
"2022": 14
}

venue_type_stats:
{
"journals": 1,
"conf": 24
}