{"list":"other","total":203,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"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":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"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":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"2308.00352","title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","created":"2023-08-01","cited_by_count":1808},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"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":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162},{"id":"2304.05128","title":"Teaching Large Language Models to Self-Debug","created":"2023-04-11","cited_by_count":988},{"id":"2307.07924","title":"ChatDev: Communicative Agents for Software Development","created":"2023-07-16","cited_by_count":919},{"id":"2112.00114","title":"Show Your Work: Scratchpads for Intermediate Computation with Language Models","created":"2021-11-30","cited_by_count":886},{"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":"2306.15595","title":"Extending Context Window of Large Language Models via Positional Interpolation","created":"2023-06-27","cited_by_count":740},{"id":"2306.08568","title":"WizardCoder: Empowering Code Large Language Models with Evol-Instruct","created":"2023-06-14","cited_by_count":733},{"id":"1911.02150","title":"Fast Transformer Decoding: One Write-Head is All You Need","created":"2019-11-06","cited_by_count":717},{"id":"2305.08322","title":"C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models","created":"2023-05-15","cited_by_count":708},{"id":"2305.03111","title":"Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs","created":"2023-05-04","cited_by_count":688},{"id":"1709.00103","title":"Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning","created":"2017-08-31","cited_by_count":687},{"id":"2309.10305","title":"Baichuan 2: Open Large-scale Language Models","created":"2023-09-19","cited_by_count":670},{"id":"1909.09436","title":"CodeSearchNet Challenge: Evaluating the State of Semantic Code Search","created":"2019-09-20","cited_by_count":654},{"id":"2303.08128","title":"ViperGPT: Visual Inference via Python Execution for Reasoning","created":"2023-03-14","cited_by_count":603},{"id":"2309.00071","title":"YaRN: Efficient Context Window Extension of Large Language Models","created":"2023-08-31","cited_by_count":601},{"id":"2306.11644","title":"Textbooks Are All You Need","created":"2023-06-20","cited_by_count":569},{"id":"2309.05463","title":"Textbooks Are All You Need II: phi-1.5 technical report","created":"2023-09-11","cited_by_count":565},{"id":"2009.10297","title":"CodeBLEU: a Method for Automatic Evaluation of Code Synthesis","created":"2020-09-22","cited_by_count":479},{"id":"2304.11015","title":"DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction","created":"2023-04-21","cited_by_count":477},{"id":"2306.09212","title":"CMMLU: Measuring massive multitask language understanding in Chinese","created":"2023-06-15","cited_by_count":449},{"id":"2308.10620","title":"Large Language Models for Software Engineering: A Systematic Literature Review","created":"2023-08-21","cited_by_count":399},{"id":"2308.15363","title":"Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation","created":"2023-08-29","cited_by_count":385},{"id":"2303.12570","title":"RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation","created":"2023-03-22","cited_by_count":367},{"id":"2306.03091","title":"RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems","created":"2023-06-05","cited_by_count":353},{"id":"2305.07922","title":"CodeT5+: Open Code Large Language Models for Code Understanding and Generation","created":"2023-05-13","cited_by_count":333},{"id":"2305.15408","title":"Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective","created":"2023-05-24","cited_by_count":294},{"id":"2304.07590","title":"Self-collaboration Code Generation via ChatGPT","created":"2023-04-15","cited_by_count":258},{"id":"2207.14255","title":"Efficient Training of Language Models to Fill in the Middle","created":"2022-07-28","cited_by_count":255},{"id":"2309.07544","title":"VerilogEval: Evaluating Large Language Models for Verilog Code Generation","created":"2023-09-14","cited_by_count":252},{"id":"2212.12017","title":"OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization","created":"2022-12-22","cited_by_count":236},{"id":"2308.00708","title":"VeriGen: A Large Language Model for Verilog Code Generation","created":"2023-07-28","cited_by_count":200},{"id":"2310.11248","title":"CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion","created":"2023-10-17","cited_by_count":183},{"id":"2301.03988","title":"SantaCoder: don't reach for the stars!","created":"2023-01-09","cited_by_count":170},{"id":"2307.07221","title":"Software Testing with Large Language Models: Survey, Landscape, and Vision","created":"2023-07-14","cited_by_count":166},{"id":"2308.07921","title":"Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification","created":"2023-08-15","cited_by_count":166},{"id":"2308.05345","title":"RTLLM: An Open-Source Benchmark for Design RTL Generation with Large Language Model","created":"2023-08-10","cited_by_count":148},{"id":"2309.12499","title":"CodePlan: Repository-level Coding using LLMs and Planning","created":"2023-09-21","cited_by_count":140},{"id":"1711.04436","title":"SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning","created":"2017-11-13","cited_by_count":135},{"id":"2305.02309","title":"CodeGen2: Lessons for Training LLMs on Programming and Natural Languages","created":"2023-05-03","cited_by_count":125},{"id":"2304.09102","title":"Solving Math Word Problems by Combining Language Models With Symbolic Solvers","created":"2023-04-16","cited_by_count":124},{"id":"2303.13547","title":"A comprehensive evaluation of ChatGPT's zero-shot Text-to-SQL capability","created":"2023-03-12","cited_by_count":119},{"id":"2307.04349","title":"RLTF: Reinforcement Learning from Unit Test Feedback","created":"2023-07-10","cited_by_count":114},{"id":"2305.04764","title":"ChatUniTest: A Framework for LLM-Based Test Generation","created":"2023-05-08","cited_by_count":96},{"id":"2212.10481","title":"Execution-Based Evaluation for Open-Domain Code Generation","created":"2022-12-20","cited_by_count":91},{"id":"1902.01069","title":"A Comprehensive Exploration on WikiSQL with Table-Aware Word Contextualization","created":"2019-02-04","cited_by_count":88},{"id":"2308.04748","title":"Fuzz4All: Universal Fuzzing with Large Language Models","created":"2023-08-09","cited_by_count":88},{"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":"2304.10778","title":"Evaluating the Code Quality of AI-Assisted Code Generation Tools: An Empirical Study on GitHub Copilot, Amazon CodeWhisperer, and ChatGPT","created":"2023-04-21","cited_by_count":71},{"id":"2008.06448","title":"Loghub: A Large Collection of System Log Datasets for AI-driven Log Analytics","created":"2020-08-14","cited_by_count":70},{"id":"2307.14936","title":"PanGu-Coder2: Boosting Large Language Models for Code with Ranking Feedback","created":"2023-07-27","cited_by_count":69},{"id":"2308.11396","title":"Towards an Understanding of Large Language Models in Software Engineering Tasks","created":"2023-08-22","cited_by_count":68},{"id":"2303.07839","title":"ChatGPT Prompt Patterns for Improving Code Quality, Refactoring, Requirements Elicitation, and Software Design","created":"2023-03-11","cited_by_count":66},{"id":"2212.10007","title":"CoCoMIC: Code Completion By Jointly Modeling In-file and Cross-file Context","created":"2022-12-20","cited_by_count":65},{"id":"2004.03814","title":"Bao: Learning to Steer Query Optimizers","created":"2020-04-08","cited_by_count":62},{"id":"2305.11853","title":"How to Prompt LLMs for Text-to-SQL: A Study in Zero-shot, Single-domain, and Cross-domain Settings","created":"2023-05-19","cited_by_count":58},{"id":"2208.01448","title":"AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model","created":"2022-08-02","cited_by_count":57},{"id":"2310.04951","title":"CodeTransOcean: A Comprehensive Multilingual Benchmark for Code Translation","created":"2023-10-08","cited_by_count":57},{"id":"2206.08474","title":"XLCoST: A Benchmark Dataset for Cross-lingual Code Intelligence","created":"2022-06-16","cited_by_count":56},{"id":"2301.03270","title":"A Survey of Learning-based Automated Program Repair","created":"2023-01-09","cited_by_count":55},{"id":"2308.03427","title":"TPTU: Large Language Model-based AI Agents for Task Planning and Tool Usage","created":"2023-08-07","cited_by_count":55},{"id":"2208.13629","title":"A Survey on Text-to-SQL Parsing: Concepts, Methods, and Future Directions","created":"2022-08-29","cited_by_count":52},{"id":"2309.07062","title":"Large Language Models for Compiler Optimization","created":"2023-09-11","cited_by_count":52},{"id":"2308.12697","title":"Prompt-Enhanced Software Vulnerability Detection Using ChatGPT","created":"2023-08-24","cited_by_count":51},{"id":"2308.16557","title":"Effective Test Generation Using Pre-trained Large Language Models and Mutation Testing","created":"2023-08-31","cited_by_count":51},{"id":"2208.05950","title":"Interactive Code Generation via Test-Driven User-Intent Formalization","created":"2022-08-11","cited_by_count":50},{"id":"2308.01240","title":"Evaluating Instruction-Tuned Large Language Models on Code Comprehension and Generation","created":"2023-08-02","cited_by_count":50},{"id":"2207.11280","title":"PanGu-Coder: Program Synthesis with Function-Level Language Modeling","created":"2022-07-22","cited_by_count":48},{"id":"2303.03004","title":"xCodeEval: A Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and Retrieval","created":"2023-03-06","cited_by_count":47},{"id":"2308.04838","title":"No Need to Lift a Finger Anymore? Assessing the Quality of Code Generation by ChatGPT","created":"2023-08-09","cited_by_count":47},{"id":"2308.11148","title":"LLaMA-Reviewer: Advancing Code Review Automation with Large Language Models through Parameter-Efficient Fine-Tuning","created":"2023-08-22","cited_by_count":47},{"id":"2305.12586","title":"Enhancing Few-shot Text-to-SQL Capabilities of Large Language Models: A Study on Prompt Design Strategies","created":"2023-05-21","cited_by_count":45},{"id":"2308.09895","title":"Knowledge Transfer from High-Resource to Low-Resource Programming Languages for Code LLMs","created":"2023-08-19","cited_by_count":45},{"id":"2305.04118","title":"Exploring Human-Like Translation Strategy with Large Language Models","created":"2023-05-06","cited_by_count":44},{"id":"2106.05006","title":"Text-to-SQL in the Wild: A Naturally-Occurring Dataset Based on Stack Exchange Data","created":"2021-06-09","cited_by_count":43},{"id":"2201.07311","title":"Datasheet for the Pile","created":"2022-01-13","cited_by_count":43}],"next_cursor":"100"}