{"list":"other","total":88,"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":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"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":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"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":"2305.15334","title":"Gorilla: Large Language Model Connected with Massive APIs","created":"2023-05-24","cited_by_count":1332},{"id":"2304.05128","title":"Teaching Large Language Models to Self-Debug","created":"2023-04-11","cited_by_count":988},{"id":"2105.09938","title":"Measuring Coding Challenge Competence With APPS","created":"2021-05-20","cited_by_count":902},{"id":"2211.14275","title":"Solving math word problems with process- and outcome-based feedback","created":"2022-11-25","cited_by_count":901},{"id":"2112.00114","title":"Show Your Work: Scratchpads for Intermediate Computation with Language Models","created":"2021-11-30","cited_by_count":886},{"id":"2203.13474","title":"CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis","created":"2022-03-25","cited_by_count":885},{"id":"2302.00093","title":"Large Language Models Can Be Easily Distracted by Irrelevant Context","created":"2023-01-31","cited_by_count":841},{"id":"2305.06161","title":"StarCoder: may the source be with you!","created":"2023-05-09","cited_by_count":799},{"id":"2306.08568","title":"WizardCoder: Empowering Code Large Language Models with Evol-Instruct","created":"2023-06-14","cited_by_count":733},{"id":"1909.09436","title":"CodeSearchNet Challenge: Evaluating the State of Semantic Code Search","created":"2019-09-20","cited_by_count":654},{"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":"2305.18654","title":"Faith and Fate: Limits of Transformers on Compositionality","created":"2023-05-29","cited_by_count":503},{"id":"2204.05999","title":"InCoder: A Generative Model for Code Infilling and Synthesis","created":"2022-04-12","cited_by_count":498},{"id":"2211.11501","title":"DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation","created":"2022-11-18","cited_by_count":452},{"id":"2309.12288","title":"The Reversal Curse: LLMs trained on \"A is B\" fail to learn \"B is A\"","created":"2023-09-21","cited_by_count":407},{"id":"2207.10397","title":"CodeT: Code Generation with Generated Tests","created":"2022-07-21","cited_by_count":384},{"id":"2303.12570","title":"RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation","created":"2023-03-22","cited_by_count":367},{"id":"2207.01780","title":"CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning","created":"2022-07-05","cited_by_count":358},{"id":"2302.12813","title":"Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback","created":"2023-02-24","cited_by_count":353},{"id":"2306.03091","title":"RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems","created":"2023-06-05","cited_by_count":353},{"id":"2401.00595","title":"State of What Art? A Call for Multi-Prompt LLM Evaluation","created":"2023-12-31","cited_by_count":310},{"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":"2006.03511","title":"Unsupervised Translation of Programming Languages","created":"2020-06-05","cited_by_count":263},{"id":"2305.15717","title":"The False Promise of Imitating Proprietary LLMs","created":"2023-05-25","cited_by_count":263},{"id":"2307.02477","title":"Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks","created":"2023-07-05","cited_by_count":246},{"id":"2302.08468","title":"LEVER: Learning to Verify Language-to-Code Generation with Execution","created":"2023-02-16","cited_by_count":239},{"id":"2301.13196","title":"Looped Transformers as Programmable Computers","created":"2023-01-30","cited_by_count":237},{"id":"2304.03439","title":"Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4","created":"2023-04-07","cited_by_count":202},{"id":"2310.16028","title":"What Algorithms can Transformers Learn? A Study in Length Generalization","created":"2023-10-24","cited_by_count":199},{"id":"2306.09896","title":"Is Self-Repair a Silver Bullet for Code Generation?","created":"2023-06-16","cited_by_count":197},{"id":"2303.05510","title":"Planning with Large Language Models for Code Generation","created":"2023-03-09","cited_by_count":182},{"id":"2310.03533","title":"Large Language Models for Software Engineering: Survey and Open Problems","created":"2023-10-05","cited_by_count":181},{"id":"1808.01400","title":"code2seq: Generating Sequences from Structured Representations of Code","created":"2018-08-04","cited_by_count":179},{"id":"2301.03988","title":"SantaCoder: don't reach for the stars!","created":"2023-01-09","cited_by_count":170},{"id":"2310.15164","title":"LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers","created":"2023-10-23","cited_by_count":168},{"id":"2210.14868","title":"Multi-lingual Evaluation of Code Generation Models","created":"2022-10-26","cited_by_count":159},{"id":"2208.08227","title":"MultiPL-E: A Scalable and Extensible Approach to Benchmarking Neural Code Generation","created":"2022-08-17","cited_by_count":136},{"id":"2210.14179","title":"Practical Program Repair in the Era of Large Pre-trained Language Models","created":"2022-10-25","cited_by_count":133},{"id":"2204.11454","title":"Natural Language to Code Translation with Execution","created":"2022-04-25","cited_by_count":124},{"id":"2307.03381","title":"Teaching Arithmetic to Small Transformers","created":"2023-07-07","cited_by_count":123},{"id":"2303.07263","title":"InferFix: End-to-End Program Repair with LLMs","created":"2023-03-13","cited_by_count":114},{"id":"2206.12839","title":"Repository-Level Prompt Generation for Large Language Models of Code","created":"2022-06-26","cited_by_count":106},{"id":"2302.07867","title":"Learning Performance-Improving Code Edits","created":"2023-02-15","cited_by_count":106},{"id":"2112.02969","title":"Jigsaw: Large Language Models meet Program Synthesis","created":"2021-12-06","cited_by_count":103},{"id":"2212.10264","title":"ReCode: Robustness Evaluation of Code Generation Models","created":"2022-12-20","cited_by_count":103},{"id":"2205.11502","title":"On the Paradox of Learning to Reason from Data","created":"2022-05-23","cited_by_count":93},{"id":"2212.10481","title":"Execution-Based Evaluation for Open-Domain Code Generation","created":"2022-12-20","cited_by_count":91},{"id":"2212.09248","title":"Natural Language to Code Generation in Interactive Data Science Notebooks","created":"2022-12-19","cited_by_count":87},{"id":"2302.05020","title":"Impact of Code Language Models on Automated Program Repair","created":"2023-02-10","cited_by_count":85},{"id":"2311.08516","title":"LLMs cannot find reasoning errors, but can correct them given the error location","created":"2023-11-14","cited_by_count":85},{"id":"2211.16490","title":"Coder Reviewer Reranking for Code Generation","created":"2022-11-29","cited_by_count":84},{"id":"2207.14502","title":"Language Models Can Teach Themselves to Program Better","created":"2022-07-29","cited_by_count":78},{"id":"2105.03519","title":"Understanding by Understanding Not: Modeling Negation in Language Models","created":"2021-05-07","cited_by_count":73},{"id":"2307.14936","title":"PanGu-Coder2: Boosting Large Language Models for Code with Ranking Feedback","created":"2023-07-27","cited_by_count":69},{"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":"2303.09384","title":"LLMSecEval: A Dataset of Natural Language Prompts for Security Evaluations","created":"2023-03-16","cited_by_count":62},{"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":"2108.11590","title":"AVATAR: A Parallel Corpus for Java-Python Program Translation","created":"2021-08-26","cited_by_count":59},{"id":"1707.02275","title":"A parallel corpus of Python functions and documentation strings for automated code documentation and code generation","created":"2017-07-07","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":"2310.07923","title":"The Expressive Power of Transformers with Chain of Thought","created":"2023-10-11","cited_by_count":50},{"id":"1910.02216","title":"JuICe: A Large Scale Distantly Supervised Dataset for Open Domain Context-based Code Generation","created":"2019-10-05","cited_by_count":49},{"id":"2305.14591","title":"ALGO: Synthesizing Algorithmic Programs with LLM-Generated Oracle Verifiers","created":"2023-05-24","cited_by_count":41},{"id":"2308.03762","title":"GPT-4 Can't Reason","created":"2023-07-21","cited_by_count":40},{"id":"2305.04032","title":"ToolCoder: Teach Code Generation Models to use API search tools","created":"2023-05-06","cited_by_count":37},{"id":"2305.05383","title":"Code Execution with Pre-trained Language Models","created":"2023-05-08","cited_by_count":34},{"id":"2305.15507","title":"The Larger They Are, the Harder They Fail: Language Models do not Recognize Identifier Swaps in Python","created":"2023-05-24","cited_by_count":29},{"id":"2105.14220","title":"CoDesc: A Large Code-Description Parallel Dataset","created":"2021-05-29","cited_by_count":23},{"id":"2305.14699","title":"Can Transformers Learn to Solve Problems Recursively?","created":"2023-05-24","cited_by_count":17},{"id":"2309.16120","title":"Fixing Large Language Models' Specification Misunderstanding for Better Code Generation","created":"2023-09-28","cited_by_count":17},{"id":"2303.09564","title":"TypeT5: Seq2seq Type Inference using Static Analysis","created":"2023-03-16","cited_by_count":12},{"id":"2210.00848","title":"Toward Trustworthy Neural Program Synthesis","created":"2022-09-29","cited_by_count":11},{"id":"2206.13619","title":"DeepPERF: A Deep Learning-Based Approach For Improving Software Performance","created":"2022-06-27","cited_by_count":6},{"id":"2202.07612","title":"CodeGen-Test: An Automatic Code Generation Model Integrating Program Test Information","created":"2022-02-14","cited_by_count":3}],"next_cursor":null}