/LLM4SE

Large Language Models for Software Engineering

Primary LanguagePython

Large Language Model for Software Engineering

The collection is actively updated with the help of an internal literature search engine.

Table of Contents

| Code Model List | | Popular Code Model List | | Paper List | | Paper Stats | | Recent Preprints |

Model List

2023 (234 Models)

Click to expand!
NoCrypt/fast-repo TabbyML/SantaCoder-1B michaelfeil/ct2fast-starchat-alpha
mantra-coding/alBERTo michaelfeil/ct2fast-starcoderbase michaelfeil/ct2fast-starcoder
bigcode/tiny_starcoder_py kevinpro/Vicuna-13B-CoT jiezhou1996/test
Soliai/Soli bigcode/gpt_bigcode-santacoder michaelfeil/ct2fast-gpt_bigcode-santacoder
dushigao/yolov4 bigcode/starcoder rustformers/bloom-ggml
rustformers/bloomz-ggml mishasadhaker/codet5_large_typescript sahil2801/instruct-codegen-16B
jokerLang/aa CNXT/CHaTx sadiqj/camlcoder
omegaodin/replit-replit-code-v1-3b replit/replit-code-v1-3b teknium/Replit-v1-CodeInstruct-3B-fp16
teknium/Replit-v1-CodeInstruct-3B kkhan/gpt2-medium-iba-txt 4bit/Replit-v1-CodeInstruct-3B
bigscience/bloomz-560m bigscience/bloomz-1b1 bigscience/bloomz-1b7
bigscience/bloomz-3b bigscience/bloomz-7b1 bigscience/bloomz
Neupane9Sujal/Text_Summarization betelguesestudios/ChatDBD azizp128/emotion-predictor-indobert
zirui3/starcoder-ft-zh zjunlp/CaMA-13B-LoRA zjunlp/CaMA-13B-Diff
Aryan2003/roberta_job zchflyer/test11 EnterNameBros/DialoGPT-small-Senko-san-ver-2
dev2bit/es2bash-mt5 omegaodin/gpt2 Fsoft-AIC/Codebert-docstring-inconsistency
HuggingFaceH4/starchat-alpha AsakusaRinne/LLamaSharpSamples AlexWortega/wortegaLM-1b
huolongguo10/check_sec_tiny NeoDim/starcoder-GGML NeoDim/starcoderbase-GGML
NeoDim/starchat-alpha-GGML christinacdl/moderate_severe_depression_model KinglyCrow/pythia-3b-deduped-sft-r1-python-finetuned
Binaryy/blender-bot-distill-finetuned Fredithefish/CrimsonPajama showpiece/donut4cover_of_books
OdiaGenAI/odiagenAI-model-v1 NatLee/openpose-keras-model pratikcha/DummyModelTest
up201806461/BFP-combined baotoan2002/GPT-2 brandit/atharv.1
BlackBull/yeet wandisun/generate_testcase pszemraj/bart-large-code-instructiongen
redlinezh/redlinezh erichilarysmithsr/Quality-of-Life-Games AlexWortega/wortegaLM
rishiraj/starchat bigcode/starcoder-megatron bigcode/starcoderbase-megatron
bigcode/santacoder bigscience/bloom-1b7 bigscience/bloom-560m
bigcode/starpii bigcode/starcoderbase APJ23/MultiHeaded_Sentiment_Analysis_Model
lentan/replit bigcode/starencoder jitesh/emotion-english
TinaLiHF/fined-tuned-T5small tmnam20/codebert-code-summarization Vipitis/santacoder-finetuned-the-stack-glsl
Vipitis/santacoder-finetuned-Shadertoys-fine Vipitis/santacoder-finetuned-Shadertoys tabbleman/test
huolongguo10/check_sec HelloImSteven/AppleScript-Summarizer duncan93/video
alexpaul/QI-Large-v1 JeanL-0/ChatAnswering-PTBR jitroy07/BOT
Rirou360/test RafMuz/alpaca7B-lora Akhil0-o/saved_model_links
TrippingFollowing39/AMOGUS Akhil0-o/saved_model_body MrRainbow/RainbowGPT
Akhil0-o/Phishing_detection Ilangraterol/Dataset_model AlexWortega/instruct_rugptlarge
MLRush/chinese-chat-30m MLRush/chinese-lm-30m ParsaKgvr/mmdGPT
ParsaKgvr/mmdBERT dorkai/codeX-1.0 OtterDev/otterchat
Phonecharger/WLAsw1 MatthiasPi/ActiveLearningModel-WAR-WassersteinActiveRegression Wannita/baseline_codecompletion
ybelkada/bloom-1b7-8bit kelly233/test_model ArmelR/AlpacaCode512
bigscience/bloom-3b lambdasec/santafixer ybelkada/bloom-560m-8bit
PromptKing/GTA5_PROCESS_LEARNING_AI Qrstud/ANCs HTP/CHaTx
LYFCJJ/anythingv45-cjj-diffusers hakurei/instruct-12b Dirus/GPTOWN
TeamGZG/toxic-comment-classification-project MarTinSForZZa/Innerversal newsrx/bloomz-7b1
0x7194633/pyGPT-50M dhnchandan/huggingface RomanTeucher/PythonCoder
bigscience/bloom edbeeching/llama-se-rl-adapter TheEeeeLin/test
olivierdehaene/optimized-santacoder Mauquoi-00/Teenage_Gender_Classification Esly35i/Esmoli
zee2221/ai_me urmom12349823/AItext manstepharder/hangi
Sentdex/GPyT lxe/Cerebras-GPT-2.7B-Alpaca-SP akone/bloomgpt
TSjB/mbart-large-52-qm-ru-v1 Wannita/PyCoder mazeratti/creative
TabbyML/NeoX-1.3B pszemraj/bart-base-code-instructiongen AlexWortega/instruct_rugptMedium
vernin/maylora valooo/test amongusrickroll68/MeloMind
amongusrickroll68/TextImagine-1.0-March-2023 badmatr11x/distilroberta-base-offensive-hateful-speech-text-multiclassification Techh/speed_car_policee
Ar4ikov/gpt2-650k-stable-diffusion-prompt-generator bigscience/distill-bloom-1b3 CAUKiel/JavaBERT
emre/java-RoBERTa-Tara-small Ashokajou51/NonToxicCivilBert thevyasamit/bert_fake_news_classification
namikazi25/DCNN_on_CIFAR_10 mdoshi2612/fake-news-detector CAUKiel/JavaBERT-uncased
shibing624/code-autocomplete-distilgpt2-python shibing624/code-autocomplete-gpt2-base aarnphm/multi-length-text-classification-pipeline
NITINNANNAPANENI/Ll rockmiin/ml-codeparrot Naina07/Fine_tune
bigscience/bloom-1b1 bigscience/distill-bloom-1b3-10x wittyicon/Text-Alchemy
razent/cotext-1-cc omarelsayeed/wav2vec2_ar_anz2 whybeyoung/test
KonghaYao/MagicPrompt_SD_V1 zabir-alnazi/fatima-fellowship-ai-gen-detector Abdullah007/image-classification-ResNet50
AlexWortega/instruct_rugptSmall sjiang1/codecse daeunj/828A
Ajibola/PaViT changwh5/BigBiGAN-MNIST-150epoch Azarthehulk/Image_preprocessing_basics
nishakathiriya/DR-model AcrossTheUniverseZ/ATUZGenerator Roy029/sno_empty
imharesh/Shabbat pavanBuduguppa/asr_inverse_text_normalization NeyroTech/PicKHK
rapples/png2emb AlexWortega/taskGPT2-xl-v0.2a marlenezw/AutoVC_Voice_Conversion
mrm8488/santacoder-finetuned-the-stack-clojure BrendaTellez/sounds BrendaTellez/SoundClassificationCNNRNN
samkenxstream/AlgoSilicon samkenxstream/HierarchyMartialsAI ilahazs/rokashibasakiv1
bigscience/bloom-7b1 bigscience/bloom-560m-intermediate bigscience/bloom-1b1-intermediate
bigscience/bloom-3b-intermediate bigscience/bloom-7b1-intermediate bigscience/bloomz-mt
bigscience/bloomz-7b1-mt bigscience/bloomz-7b1-p3 bigscience/bloomz-p3
bigscience/bloom-1b7-intermediate mrm8488/santacoder-finetuned-the-stack-swift Neighhhbor/Test_model
muhtasham/santacoder-finetuned-the-stack-cobol muhtasham/santacoder-finetuned-the-stack-assembly HuggingFaceH4/bloomz-7b1
zkep/detr loubnabnl/santacoder-code-to-text mrm8488/santacoder-finetuned-the-stack-bash-shell
Thyral/Testing noahshinn024/santacoder-ts el-profesor/code_t5
K8778/universe CarperAI/diff-codegen-6b-v2 CarperAI/diff-codegen-2b-v2
CarperAI/diff-codegen-350m-v2 96harsh56/bert_test2 aminian/ML-final-project
microsoft/codereviewer facebook/incoder-1B facebook/incoder-6B
MrFitzmaurice/roberta-finetuned-topic-5 mble/nameToStdName aadvari/movie-recommender
aparnabhat/kannada-ner Kaliel456/Lynn bigcode/santacoder-megatron
Salesforce/codegen2-1B Salesforce/codegen2-3_7B Salesforce/codegen2-7B

2022 (38 Models)

Click to expand!
mrm8488/bloom-560m-finetuned-the-stack-rust smallcloudai/codify_medium_multi smallcloudai/codify_3b_multi
anjandash/JavaBERT-small anjandash/JavaBERT-mini saikatc/NatGen
Nokia/nlgp-docstring alecsharpie/codegen_350m_html alecsharpie/codegen_350m_css
CarperAI/diff-codegen-350m-v1 giulio98/codegen-350M-multi-xlcost-v2 giulio98/codegen-350M-multi-xlcost
Nokia/nlgp-natural model-attribution-challenge/bloom-560m CarperAI/FIM-NeoX-1.3B
model-attribution-challenge/bloom-2b5 huggingface/CodeBERTa-language-id codeparrot/codeparrot-small-code-to-text
moyix/csrc_774m codeparrot/unixcoder-java-complexity-prediction codeparrot/codeparrot-small-text-to-code
bigscience/bloom-optimizer-states model-attribution-challenge/bloom-350m little-star/good_model
codeparrot/codeparrot-small-multi bigscience/bloom-intermediate bigscience/tr11-176B-logs
codeparrot/codeparrot-small huggingface/CodeBERTa-small-v1 codeparrot/codeparrot
lvwerra/test_card razent/spbert-mlm-base razent/spbert-mlm-wso-base
razent/spbert-mlm-zero razent/cotext-2-cc razent/cotext-1-ccg
ietz/distilroberta-base-finetuned-jira-qt-issue-titles-and-bodies ietz/distilroberta-base-finetuned-jira-qt-issue-title

2021 (2 Models)

Click to expand!
mrm8488/codeBERTaJS mrm8488/CodeBERTaPy

Popular Model List

Year-Id Model Name Paper # of Parameters Open Source?
2023-4 CodeGen2 link [1B, 3.7B, 7B, 16B] source
2023-3 CodeT5+ link [220M, 770M, 2B, 6B, 16B] source
2023-2 StarCoder link [15B] source
2023-1 CodeGeeX link [13B] source
2022-2 InCoder link [1.3B, 6B] source
2022-1 CodeGen link [350M, 2B, 6B, 16B] source
2021-1 CodeT5 link [770M] source
2020-2 GraphCodeBERT link source
2020-1 CodeBERT link [125M] source

Paper List

Survey Papers

Year Title
2023 A Survey of Trojans in Neural Models of Source Code: Taxonomy and Techniques
2023 Towards an Understanding of Large Language Models in Software Engineering Tasks
2023 A Survey of Large Language Models for Code: Evolution, Benchmarking, and Future Trends
2023 Large Language Models for Software Engineering: Survey and Open Problems
2023 Large Language Models for Software Engineering: A Systematic Literature Review
2023 Software Testing with Large Language Model: Survey, Landscape, and Vision

Task Tags

Click to expand!
Year-Id Title Venue Name
2023-33 Flakify: A Black-Box, Language Model-Based Predictor for Flaky Tests. TSE
2023-32 Do Pretrained Language Models Indeed Understand Software Engineering Tasks? TSE
2023-31 CodaMosa: Escaping Coverage Plateaus in Test Generation with Pre-trained Large Language Models. ICSE
2023-30 Impact of Code Language Models on Automated Program Repair. ICSE
2023-29 Automated Repair of Programs from Large Language Models. ICSE
2023-28 Automated Program Repair in the Era of Large Pre-trained Language Models. ICSE
2023-27 Recommending Root-Cause and Mitigation Steps for Cloud Incidents using Large Language Models. ICSE
2023-26 Large Language Models are Few-shot Testers: Exploring LLM-based General Bug Reproduction. ICSE
2023-25 On the Applicability of Language Models to Block-Based Programs. ICSE
2023-24 The Devil is in the Tails: How Long-Tailed Code Distributions Impact Large Language Models. ASE
2023-23 CAT-LM Training Language Models on Aligned Code And Tests. ASE
2023-22 Domain Adaptive Code Completion via Language Models and Decoupled Domain Databases. ASE
2023-21 The Plastic Surgery Hypothesis in the Era of Large Language Models. ASE
2023-20 An Empirical Study on Fine-Tuning Large Language Models of Code for Automated Program Repair. ASE
2023-19 SMT Solver Validation Empowered by Large Pre-Trained Language Models. ASE
2023-18 Towards Autonomous Testing Agents via Conversational Large Language Models. ASE
2023-17 Model-Agnostic Syntactical Information for Pre-Trained Programming Language Models. MSR
2023-16 Large Language Models and Simple, Stupid Bugs. MSR
2023-15 She Elicits Requirements and He Tests: Software Engineering Gender Bias in Large Language Models. MSR
2023-14 Copiloting the Copilots: Fusing Large Language Models with Completion Engines for Automated Program Repair. FSE
2023-13 Multilingual Code Co-evolution using Large Language Models. FSE
2023-12 Baldur: Whole-Proof Generation and Repair with Large Language Models. FSE
2023-11 On the Usage of Continual Learning for Out-of-Distribution Generalization in Pre-trained Language Models of Code. FSE
2023-10 Grace: Language Models Meet Code Edits. FSE
2023-9 Assess and Summarize: Improve Outage Understanding with Large Language Models. FSE
2023-8 Getting pwn'd by AI: Penetration Testing with Large Language Models. FSE
2023-7 Assisting Static Analysis with Large Language Models: A ChatGPT Experiment. FSE
2023-6 A Language Model of Java Methods with Train/Test Deduplication. FSE
2023-5 Extending Source Code Pre-Trained Language Models to Summarise Decompiled Binarie. SANER
2023-4 Large Language Models: The Next Frontier for Variable Discovery within Metamorphic Testing? SANER
2023-3 How Robust Is a Large Pre-trained Language Model for Code GenerationÆ’ A Case on Attacking GPT2. SANER
2023-2 Large Language Models Are Zero-Shot Fuzzers: Fuzzing Deep-Learning Libraries via Large Language Models. ISSTA
2023-1 Harnessing Large Language Models for Simulink Toolchain Testing and Developing Diverse Open-Source Corpora of Simulink Models for Metric and Evolution Analysis. ISSTA
2022-27 Fast Changeset-based Bug Localization with BERT ICSE
2022-26 An Empirical Study on the Usage of Transformer Models for Code Completion TSE
2022-25 DualSC: Automatic Generation and Summarization of Shellcode via Transformer and Dual Learning SANER
2022-24 Source Code Summarization with Structural Relative Position Guided Transformer SANER
2022-23 Aspect-Based API Review Classification: How Far Can Pre-Trained Transformer Model Go? SANER
2022-22 Can Identifier Splitting Improve Open-Vocabulary Language Model of Code? SANER
2022-21 Evaluation of Context-Aware Language Models and Experts for Effort Estimation of Software Maintenance Issues ICSME
2022-20 Automating code review activities by large-scale pre-training FSE
2022-19 VulCurator: A Vulnerability-fixing Commit Detector FSE
2022-18 AutoPruner: Transformer-based Call Graph Pruning FSE
2022-17 Can pre-trained code embeddings improve model performance? Revisiting the use of code embeddings in software engineering tasks EMSE
2022-16 Bridging Pre-trained Models and Downstream Tasks for Source Code Understanding ICSE
2022-15 Jigsaw: Large Language Models meet Program Synthesis ICSE
2022-14 Natural Attack for Pre-trained Models of Code ICSE
2022-13 Using Pre-Trained Models to Boost Code Review Automation ICSE
2022-12 What Do They Capture? - A Structural Analysis of Pre-Trained Language Models for Source Code ICSE
2022-11 A Light Bug Triage Framework for Applying Large Pre-trained Language Model ASE
2022-10 AST-Probe: Recovering abstract syntax trees from hidden representations of pre-trained language models ASE
2022-9 Compressing Pre-trained Models of Code into 3 MB ASE
2022-8 PRCBERT: Prompt Learning for Requirement Classification using BERT-based Pretrained Language Models ASE
2022-7 Prompt-tuned Code Language Model as a Neural Knowledge Base for Type Inference in Statically-Typed Partial Code ASE
2022-6 Few-shot training LLMs for project-specific code-summarization ASE
2022-5 Diet code is healthy: simplifying programs for pre-trained models of code FSE
2022-4 Discrepancies among pre-trained deep neural networks: a new threat to model zoo reliability FSE
2022-3 Effective and scalable fault injection using bug reports and generative language models FSE
2022-2 An extensive study on pre-trained models for program understanding and generation ISSTA
2022-1 Using pre-trained language models to resolve textual and semantic merge conflicts (experience paper) ISSTA
2021-7 Studying the Usage of Text-To-Text Transfer Transformer to Support Code-Related Tasks ICSE
2021-6 Traceability Transformed: Generating more Accurate Links with Pre-Trained BERT Models ICSE
2021-5 Code Prediction by Feeding Trees to Transformers ICSE
2021-4 Traceability Transformed: Generating more Accurate Links with Pre-Trained BERT Models ICSE
2021-3 DeepMemory: Model-based Memorization Analysis of Deep Neural Language Models ASE
2021-2 What do pre-trained code models know about code? ASE
2021-1 Does reusing pre-trained NLP model propagate bugs? FSE
2020-3 Achieving Reliable Sentiment Analysis in the Software Engineering Domain using BERT ICSME
2020-2 Sentiment Analysis for Software Engineering: How Far Can Pre-trained Transformer Models Go? ICSME
2020-1 Multi-task Learning based Pre-trained Language Model for Code Completion ASE

Paper Stats

Venue Stats

Venue Count
ICSE 17
FSE 17
ASE 16
ISSTA 4
TSE 3
TOSEM 0
EMSE 1
ICSME 3
SANER 7
MSR 3

Year Stats

Venue Count
2023 33
2022 27
2021 7
2020 3

Considered Venues

Powered by an automation tool, mainteners routinary check for new LLM4SE papers that appear in the venues below:

Conferences

  • Software Engineering Domain:
    • ICSE: International Conference on Software Engineering
    • FSE: The ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering
    • ASE: IEEE/ACM International Conference on Automated Software Engineering
    • ISSTA: International Symposium on Software Testing and Analysis
    • ICSME: IEEE International Conference on Software Maintenance and Evolution
    • MSR: IEEE Working Conference on Mining Software Repositories
    • SANER: IEEE International Conference on Software Analysis, Evolution, and Reengineering

Journals

  • Software Engineering Domain:
    • TSE: IEEE Transactions on Software Engineering
    • TOSEM: ACM Transactions on Software Engineering and Methodology
    • EMSE: Empirical Software Engineering

Contribution

The easiest way to contribute is to submit a paper with verified information via GitHub issues. Only url of the paper should be already enough. The mainteiner will add accordingly and keep you updated in the issue conversation.

Alternatively, you can create a pull request. For that, you need to strictly follow the format.

Any other suggestion to improve this repository is also highly welcomed via GitHub issues.

Contributors

maxxbw54  thanhlecongg  Xin-Zhou-smu