{"list":"other","total":51,"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":"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"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":"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":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"id":"2203.07814","title":"Competition-Level Code Generation with AlphaCode","created":"2022-02-08","cited_by_count":1462},{"id":"1610.01644","title":"Understanding intermediate layers using linear classifier probes","created":"2016-10-05","cited_by_count":1353},{"id":"2002.08155","title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","created":"2020-02-19","cited_by_count":1310},{"id":"1906.04341","title":"What Does BERT Look At? An Analysis of BERT's Attention","created":"2019-06-11","cited_by_count":1003},{"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":"2102.12452","title":"Probing Classifiers: Promises, Shortcomings, and Advances","created":"2021-02-24","cited_by_count":876},{"id":"2002.12327","title":"A Primer in BERTology: What we know about how BERT works","created":"2020-02-27","cited_by_count":815},{"id":"2102.04664","title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","created":"2021-02-09","cited_by_count":744},{"id":"1909.09436","title":"CodeSearchNet Challenge: Evaluating the State of Semantic Code Search","created":"2019-09-20","cited_by_count":654},{"id":"1909.03368","title":"Designing and Interpreting Probes with Control Tasks","created":"2019-09-08","cited_by_count":640},{"id":"2009.08366","title":"GraphCodeBERT: Pre-training Code Representations with Data Flow","created":"2020-09-17","cited_by_count":609},{"id":"2204.05999","title":"InCoder: A Generative Model for Code Infilling and Synthesis","created":"2022-04-12","cited_by_count":498},{"id":"1805.01070","title":"What you can cram into a single vector: Probing sentence embeddings for linguistic properties","created":"2018-05-03","cited_by_count":457},{"id":"1905.06316","title":"What do you learn from context? Probing for sentence structure in contextualized word representations","created":"2019-05-15","cited_by_count":438},{"id":"2103.06333","title":"Unified Pre-training for Program Understanding and Generation","created":"2021-03-10","cited_by_count":366},{"id":"2203.03850","title":"UniXcoder: Unified Cross-Modal Pre-training for Code Representation","created":"2022-03-08","cited_by_count":361},{"id":"2005.08025","title":"IntelliCode Compose: Code Generation Using Transformer","created":"2020-05-16","cited_by_count":227},{"id":"1711.00740","title":"Learning to Represent Programs with Graphs","created":"2017-11-01","cited_by_count":220},{"id":"1608.04207","title":"Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks","created":"2016-08-15","cited_by_count":216},{"id":"1808.01400","title":"code2seq: Generating Sequences from Structured Representations of Code","created":"2018-08-04","cited_by_count":179},{"id":"1704.03471","title":"What do Neural Machine Translation Models Learn about Morphology?","created":"2017-04-11","cited_by_count":166},{"id":"1808.08949","title":"Dissecting Contextual Word Embeddings: Architecture and Representation","created":"2018-08-27","cited_by_count":146},{"id":"2111.09259","title":"Acquisition of Chess Knowledge in AlphaZero","created":"2021-11-17","cited_by_count":123},{"id":"2005.07310","title":"Behind the Scene: Revealing the Secrets of Pre-trained Vision-and-Language Models","created":"2020-05-15","cited_by_count":90},{"id":"2003.07914","title":"Big Code != Big Vocabulary: Open-Vocabulary Models for Source Code","created":"2020-03-17","cited_by_count":54},{"id":"2202.06840","title":"What Do They Capture? -- A Structural Analysis of Pre-Trained Language Models for Source Code","created":"2022-02-14","cited_by_count":50},{"id":"1911.00225","title":"When Choosing Plausible Alternatives, Clever Hans can be Clever","created":"2019-11-01","cited_by_count":40},{"id":"2108.11308","title":"What do pre-trained code models know about code?","created":"2021-08-25","cited_by_count":36},{"id":"1506.01159","title":"On the \"Naturalness\" of Buggy Code","created":"2015-06-03","cited_by_count":35},{"id":"2001.00059","title":"Learning and Evaluating Contextual Embedding of Source Code","created":"2019-12-21","cited_by_count":33},{"id":"2202.08975","title":"Probing Pretrained Models of Source Code","created":"2022-02-16","cited_by_count":26},{"id":"2206.11719","title":"AST-Probe: Recovering abstract syntax trees from hidden representations of pre-trained language models","created":"2022-06-23","cited_by_count":16},{"id":"2204.07560","title":"AI-driven Development Is Here: Should You Worry?","created":"2022-04-15","cited_by_count":15},{"id":"2212.02684","title":"Codex Hacks HackerRank: Memorization Issues and a Framework for Code Synthesis Evaluation","created":"2022-12-06","cited_by_count":14},{"id":"2111.14232","title":"Long-range and hierarchical language predictions in brains and algorithms","created":"2021-11-28","cited_by_count":10},{"id":"2207.08466","title":"What does Transformer learn about source code?","created":"2022-07-18","cited_by_count":9},{"id":"2211.14673","title":"Evaluation Beyond Task Performance: Analyzing Concepts in AlphaZero in Hex","created":"2022-11-26","cited_by_count":8},{"id":"2106.15209","title":"Making the most of small Software Engineering datasets with modern machine learning","created":"2021-06-29","cited_by_count":6},{"id":"2204.08653","title":"On The Cross-Modal Transfer from Natural Language to Code through Adapter Modules","created":"2022-04-19","cited_by_count":6},{"id":"2210.04633","title":"CAT-probing: A Metric-based Approach to Interpret How Pre-trained Models for Programming Language Attend Code Structure","created":"2022-10-07","cited_by_count":6},{"id":"2110.10404","title":"JavaBERT: Training a transformer-based model for the Java programming language","created":"2021-10-20","cited_by_count":5},{"id":"2210.05506","title":"Follow-up Attention: An Empirical Study of Developer and Neural Model Code Exploration","created":"2022-10-11","cited_by_count":5},{"id":"2212.09132","title":"JEMMA: An Extensible Java Dataset for ML4Code Applications","created":"2022-12-18","cited_by_count":2}],"next_cursor":null}