| Decoding Data Quality via Synthetic Corruptions: Embedding-guided Pruning of Code Data | Dec 5, 2023 | Code GenerationHumanEval | —Unverified | 0 |
| Clover: Closed-Loop Verifiable Code Generation | Oct 26, 2023 | Code Generationmbpp | CodeCode Available | 1 |
| CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion | Oct 17, 2023 | Code CompletionHumanEval | CodeCode Available | 1 |
| Bridging Code Semantic and LLMs: Semantic Chain-of-Thought Prompting for Code Generation | Oct 16, 2023 | Code GenerationHumanEval | —Unverified | 0 |
| Large Language Model-Aware In-Context Learning for Code Generation | Oct 15, 2023 | Code GenerationContrastive Learning | —Unverified | 0 |
| CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules | Oct 13, 2023 | Code GenerationHumanEval | CodeCode Available | 1 |
| The Program Testing Ability of Large Language Models for Code | Oct 9, 2023 | HumanEvalmbpp | —Unverified | 0 |
| Enhancing Large Language Models in Coding Through Multi-Perspective Self-Consistency | Sep 29, 2023 | Code GenerationHumanEval | CodeCode Available | 0 |
| Code Llama: Open Foundation Models for Code | Aug 24, 2023 | 16kCode Generation | CodeCode Available | 6 |
| RLTF: Reinforcement Learning from Unit Test Feedback | Jul 10, 2023 | Code Generationmbpp | CodeCode Available | 1 |
| InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback | Jun 26, 2023 | BenchmarkingCode Generation | CodeCode Available | 2 |
| Textbooks Are All You Need | Jun 20, 2023 | AllCode Generation | —Unverified | 0 |
| WizardCoder: Empowering Code Large Language Models with Evol-Instruct | Jun 14, 2023 | Code GenerationHumanEval | CodeCode Available | 5 |
| LeTI: Learning to Generate from Textual Interactions | May 17, 2023 | Code GenerationEvent Argument Extraction | CodeCode Available | 1 |
| Structured Chain-of-Thought Prompting for Code Generation | May 11, 2023 | Code GenerationHumanEval | —Unverified | 0 |
| Teaching Large Language Models to Self-Debug | Apr 11, 2023 | Code GenerationLanguage Modeling | CodeCode Available | 0 |
| AceCoder: Utilizing Existing Code to Enhance Code Generation | Mar 31, 2023 | Code Generationmbpp | —Unverified | 0 |
| Improving Code Generation by Training with Natural Language Feedback | Mar 28, 2023 | Code GenerationImitation Learning | CodeCode Available | 1 |
| Underwater Object Tracker: UOSTrack for Marine Organism Grasping of Underwater Vehicles | Jan 4, 2023 | Data Augmentationmbpp | CodeCode Available | 0 |
| ReCode: Robustness Evaluation of Code Generation Models | Dec 20, 2022 | Code GenerationHumanEval | CodeCode Available | 1 |
| The Stack: 3 TB of permissively licensed source code | Nov 20, 2022 | HumanEvalmbpp | —Unverified | 0 |
| CodePAD: Sequence-based Code Generation with Pushdown Automaton | Nov 2, 2022 | Code Generationmbpp | CodeCode Available | 0 |
| MultiPL-E: A Scalable and Extensible Approach to Benchmarking Neural Code Generation | Aug 17, 2022 | BenchmarkingCode Generation | CodeCode Available | 2 |
| Interactive Code Generation via Test-Driven User-Intent Formalization | Aug 11, 2022 | Code GenerationHumanEval | —Unverified | 0 |
| CodeT: Code Generation with Generated Tests | Jul 21, 2022 | Code GenerationHumanEval | CodeCode Available | 2 |
| CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning | Jul 5, 2022 | Code GenerationDecoder | CodeCode Available | 2 |
| Fault-Aware Neural Code Rankers | Jun 4, 2022 | Code GenerationHumanEval | CodeCode Available | 1 |
| Program Synthesis with Large Language Models | Aug 16, 2021 | Few-Shot Learningmbpp | CodeCode Available | 1 |
| Interval-censored Hawkes processes | Apr 16, 2021 | mbppPoint Processes | —Unverified | 0 |
