{"list":"other","total":59,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"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":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"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":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"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":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"id":"2203.07814","title":"Competition-Level Code Generation with AlphaCode","created":"2022-02-08","cited_by_count":1462},{"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":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162},{"id":"2103.10360","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","created":"2021-03-18","cited_by_count":1031},{"id":"2310.01798","title":"Large Language Models Cannot Self-Correct Reasoning Yet","created":"2023-10-03","cited_by_count":1017},{"id":"2304.05128","title":"Teaching Large Language Models to Self-Debug","created":"2023-04-11","cited_by_count":988},{"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":"2210.02414","title":"GLM-130B: An Open Bilingual Pre-trained Model","created":"2022-10-05","cited_by_count":843},{"id":"1907.10529","title":"SpanBERT: Improving Pre-training by Representing and Predicting Spans","created":"2019-07-24","cited_by_count":834},{"id":"1506.03099","title":"Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks","created":"2015-06-09","cited_by_count":803},{"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":"2211.10435","title":"PAL: Program-aided Language Models","created":"2022-11-18","cited_by_count":652},{"id":"1511.06732","title":"Sequence Level Training with Recurrent Neural Networks","created":"2015-11-20","cited_by_count":576},{"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":"2205.05131","title":"UL2: Unifying Language Learning Paradigms","created":"2022-05-10","cited_by_count":295},{"id":"2207.14255","title":"Efficient Training of Language Models to Fill in the Middle","created":"2022-07-28","cited_by_count":255},{"id":"2302.08468","title":"LEVER: Learning to Verify Language-to-Code Generation with Execution","created":"2023-02-16","cited_by_count":239},{"id":"2308.03188","title":"Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies","created":"2023-08-06","cited_by_count":238},{"id":"2308.07124","title":"OctoPack: Instruction Tuning Code Large Language Models","created":"2023-08-14","cited_by_count":189},{"id":"2301.03988","title":"SantaCoder: don't reach for the stars!","created":"2023-01-09","cited_by_count":170},{"id":"2309.02591","title":"Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning","created":"2023-09-05","cited_by_count":170},{"id":"2201.07520","title":"CM3: A Causal Masked Multimodal Model of the Internet","created":"2022-01-19","cited_by_count":142},{"id":"1902.03249","title":"Insertion Transformer: Flexible Sequence Generation via Insertion Operations","created":"2019-02-08","cited_by_count":125},{"id":"2211.12561","title":"Retrieval-Augmented Multimodal Language Modeling","created":"2022-11-22","cited_by_count":125},{"id":"2305.02309","title":"CodeGen2: Lessons for Training LLMs on Programming and Natural Languages","created":"2023-05-03","cited_by_count":125},{"id":"2005.05339","title":"Enabling Language Models to Fill in the Blanks","created":"2020-05-11","cited_by_count":122},{"id":"2211.16490","title":"Coder Reviewer Reranking for Code Generation","created":"2022-11-29","cited_by_count":84},{"id":"2310.06830","title":"Lemur: Harmonizing Natural Language and Code for Language Agents","created":"2023-10-10","cited_by_count":72},{"id":"2107.06955","title":"HTLM: Hyper-Text Pre-Training and Prompting of Language Models","created":"2021-07-14","cited_by_count":58},{"id":"2210.11399","title":"Transcending Scaling Laws with 0.1% Extra Compute","created":"2022-10-20","cited_by_count":57},{"id":"1902.02192","title":"Non-Monotonic Sequential Text Generation","created":"2019-02-05","cited_by_count":55},{"id":"1902.01370","title":"Insertion-based Decoding with automatically Inferred Generation Order","created":"2019-02-04","cited_by_count":43},{"id":"2002.03079","title":"Blank Language Models","created":"2020-02-08","cited_by_count":43},{"id":"2306.02907","title":"SelfEvolve: A Code Evolution Framework via Large Language Models","created":"2023-06-05","cited_by_count":43},{"id":"1901.00158","title":"Text Infilling","created":"2019-01-01","cited_by_count":32},{"id":"2305.00909","title":"Outline, Then Details: Syntactically Guided Coarse-To-Fine Code Generation","created":"2023-04-28","cited_by_count":27},{"id":"1906.01604","title":"KERMIT: Generative Insertion-Based Modeling for Sequences","created":"2019-06-04","cited_by_count":22},{"id":"2303.07295","title":"Meet in the Middle: A New Pre-training Paradigm","created":"2023-03-13","cited_by_count":22},{"id":"2310.09930","title":"FiLM: Fill-in Language Models for Any-Order Generation","created":"2023-10-15","cited_by_count":13}],"next_cursor":null}