{"list":"other","total":83,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"id":"2403.07974","title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","created":"2024-03-12","cited_by_count":2004},{"id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917},{"id":"2205.10625","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","created":"2022-05-21","cited_by_count":1407},{"id":"2305.01210","title":"Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation","created":"2023-05-02","cited_by_count":1391},{"id":"2002.08155","title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","created":"2020-02-19","cited_by_count":1310},{"id":"2401.14196","title":"DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence","created":"2024-01-25","cited_by_count":1181},{"id":"2304.05128","title":"Teaching Large Language Models to Self-Debug","created":"2023-04-11","cited_by_count":988},{"id":"2109.00859","title":"CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation","created":"2021-09-02","cited_by_count":906},{"id":"2105.09938","title":"Measuring Coding Challenge Competence With APPS","created":"2021-05-20","cited_by_count":902},{"id":"2305.06161","title":"StarCoder: may the source be with you!","created":"2023-05-09","cited_by_count":799},{"id":"2305.11738","title":"CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing","created":"2023-05-19","cited_by_count":783},{"id":"2306.01116","title":"The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only","created":"2023-06-01","cited_by_count":763},{"id":"2102.04664","title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","created":"2021-02-09","cited_by_count":744},{"id":"2306.08568","title":"WizardCoder: Empowering Code Large Language Models with Evol-Instruct","created":"2023-06-14","cited_by_count":733},{"id":"2401.02954","title":"DeepSeek LLM: Scaling Open-Source Language Models with Longtermism","created":"2024-01-05","cited_by_count":642},{"id":"2406.15877","title":"BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions","created":"2024-06-22","cited_by_count":546},{"id":"2402.19173","title":"StarCoder 2 and The Stack v2: The Next Generation","created":"2024-02-29","cited_by_count":502},{"id":"2310.16789","title":"Detecting Pretraining Data from Large Language Models","created":"2023-10-25","cited_by_count":387},{"id":"2206.05802","title":"Self-critiquing models for assisting human evaluators","created":"2022-06-12","cited_by_count":380},{"id":"2103.06333","title":"Unified Pre-training for Program Understanding and Generation","created":"2021-03-10","cited_by_count":366},{"id":"2201.10005","title":"Text and Code Embeddings by Contrastive Pre-Training","created":"2022-01-24","cited_by_count":361},{"id":"2211.15533","title":"The Stack: 3 TB of permissively licensed source code","created":"2022-11-20","cited_by_count":359},{"id":"2207.01780","title":"CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning","created":"2022-07-05","cited_by_count":358},{"id":"2306.03091","title":"RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems","created":"2023-06-05","cited_by_count":353},{"id":"2303.17568","title":"CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-X","created":"2023-03-30","cited_by_count":300},{"id":"2402.00157","title":"Large Language Models for Mathematical Reasoning: Progresses and Challenges","created":"2024-01-31","cited_by_count":284},{"id":"2312.02120","title":"Magicoder: Empowering Code Generation with OSS-Instruct","created":"2023-12-04","cited_by_count":256},{"id":"2402.14658","title":"OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement","created":"2024-02-22","cited_by_count":247},{"id":"2303.05398","title":"MathPrompter: Mathematical Reasoning using Large Language Models","created":"2023-03-04","cited_by_count":236},{"id":"2310.17623","title":"Proving Test Set Contamination in Black Box Language Models","created":"2023-10-26","cited_by_count":230},{"id":"2307.04964","title":"Secrets of RLHF in Large Language Models Part I: PPO","created":"2023-07-11","cited_by_count":229},{"id":"2005.08025","title":"IntelliCode Compose: Code Generation Using Transformer","created":"2020-05-16","cited_by_count":227},{"id":"2311.01964","title":"Don't Make Your LLM an Evaluation Benchmark Cheater","created":"2023-11-03","cited_by_count":194},{"id":"2308.07124","title":"OctoPack: Instruction Tuning Code Large Language Models","created":"2023-08-14","cited_by_count":189},{"id":"2308.08493","title":"Time Travel in LLMs: Tracing Data Contamination in Large Language Models","created":"2023-08-16","cited_by_count":177},{"id":"2301.03988","title":"SantaCoder: don't reach for the stars!","created":"2023-01-09","cited_by_count":170},{"id":"1805.08949","title":"Learning to Mine Aligned Code and Natural Language Pairs from Stack Overflow","created":"2018-05-23","cited_by_count":165},{"id":"2309.12499","title":"CodePlan: Repository-level Coding using LLMs and Planning","created":"2023-09-21","cited_by_count":140},{"id":"2212.09420","title":"Large Language Models Meet NL2Code: A Survey","created":"2022-12-19","cited_by_count":138},{"id":"2303.07895","title":"The Learnability of In-Context Learning","created":"2023-03-14","cited_by_count":127},{"id":"2307.04349","title":"RLTF: Reinforcement Learning from Unit Test Feedback","created":"2023-07-10","cited_by_count":114},{"id":"2404.00971","title":"Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code","created":"2024-04-01","cited_by_count":107},{"id":"1808.09588","title":"Mapping Language to Code in Programmatic Context","created":"2018-08-29","cited_by_count":104},{"id":"2301.13816","title":"Execution-based Code Generation using Deep Reinforcement Learning","created":"2023-01-31","cited_by_count":99},{"id":"2212.10481","title":"Execution-Based Evaluation for Open-Domain Code Generation","created":"2022-12-20","cited_by_count":91},{"id":"2206.06888","title":"CERT: Continual Pre-Training on Sketches for Library-Oriented Code Generation","created":"2022-06-14","cited_by_count":87},{"id":"2210.15157","title":"Conversing with Copilot: Exploring Prompt Engineering for Solving CS1 Problems Using Natural Language","created":"2022-10-27","cited_by_count":82},{"id":"2305.04207","title":"No More Manual Tests? Evaluating and Improving ChatGPT for Unit Test Generation","created":"2023-05-07","cited_by_count":82},{"id":"2207.08281","title":"Less Training, More Repairing Please: Revisiting Automated Program Repair via Zero-shot Learning","created":"2022-07-17","cited_by_count":76},{"id":"2405.19856","title":"DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories","created":"2024-05-30","cited_by_count":72},{"id":"1906.01388","title":"A Comprehensive Study on Deep Learning Bug Characteristics","created":"2019-06-03","cited_by_count":65},{"id":"2403.04811","title":"Quantifying Contamination in Evaluating Code Generation Capabilities of Language Models","created":"2024-03-06","cited_by_count":65},{"id":"2311.07989","title":"Unifying the Perspectives of NLP and Software Engineering: A Survey on Language Models for Code","created":"2023-11-14","cited_by_count":62},{"id":"2403.08937","title":"Bugs in Large Language Models Generated Code: An Empirical Study","created":"2024-03-13","cited_by_count":60},{"id":"2401.00125","title":"LLM-Assist: Enhancing Closed-Loop Planning with Language-Based Reasoning","created":"2023-12-30","cited_by_count":59},{"id":"2310.08992","title":"CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules","created":"2023-10-13","cited_by_count":58},{"id":"2404.14646","title":"Exploring and Unleashing the Power of Large Language Models in Automated Code Translation","created":"2024-04-23","cited_by_count":57},{"id":"2306.00024","title":"Self-Verification Improves Few-Shot Clinical Information Extraction","created":"2023-05-30","cited_by_count":52},{"id":"2305.13252","title":"\"According to ...\": Prompting Language Models Improves Quoting from Pre-Training Data","created":"2023-05-22","cited_by_count":42},{"id":"2307.02503","title":"Natural Language Generation and Understanding of Big Code for AI-Assisted Programming: A Review","created":"2023-07-04","cited_by_count":32},{"id":"2308.10462","title":"Exploring Parameter-Efficient Fine-Tuning Techniques for Code Generation with Large Language Models","created":"2023-08-21","cited_by_count":28},{"id":"2311.14904","title":"LLM-Assisted Code Cleaning For Training Accurate Code Generators","created":"2023-11-25","cited_by_count":27},{"id":"2405.11430","title":"MHPP: Exploring the Capabilities and Limitations of Language Models Beyond Basic Code Generation","created":"2024-05-19","cited_by_count":26},{"id":"2311.09868","title":"INTERVENOR: Prompting the Coding Ability of Large Language Models with the Interactive Chain of Repair","created":"2023-11-16","cited_by_count":18},{"id":"2310.03173","title":"$\\mathcal{B}$-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis","created":"2023-10-04","cited_by_count":17},{"id":"2405.00204","title":"General Purpose Verification for Chain of Thought Prompting","created":"2024-04-30","cited_by_count":17},{"id":"2402.13013","title":"Code Needs Comments: Enhancing Code LLMs with Comment Augmentation","created":"2024-02-20","cited_by_count":16},{"id":"2311.07599","title":"Testing LLMs on Code Generation with Varying Levels of Prompt Specificity","created":"2023-11-10","cited_by_count":12},{"id":"2404.03823","title":"An Investigation into Misuse of Java Security APIs by Large Language Models","created":"2024-04-04","cited_by_count":11},{"id":"1909.01760","title":"An Empirical Study of the Relationships between Code Readability and Software Complexity","created":"2019-08-30","cited_by_count":3}],"next_cursor":null}