{"list":"other","total":59,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"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":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"2101.06804","title":"What Makes Good In-Context Examples for GPT-$3$?","created":"2021-01-17","cited_by_count":1195},{"id":"1809.08887","title":"Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task","created":"2018-09-24","cited_by_count":1139},{"id":"2108.12409","title":"Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation","created":"2021-08-27","cited_by_count":1103},{"id":"2004.09297","title":"MPNet: Masked and Permuted Pre-training for Language Understanding","created":"2020-04-20","cited_by_count":981},{"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":"2212.07677","title":"Transformers learn in-context by gradient descent","created":"2022-12-15","cited_by_count":732},{"id":"2109.05093","title":"PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models","created":"2021-09-10","cited_by_count":411},{"id":"2105.03075","title":"A Survey of Data Augmentation Approaches for NLP","created":"2021-05-07","cited_by_count":409},{"id":"2207.10397","title":"CodeT: Code Generation with Generated Tests","created":"2022-07-21","cited_by_count":384},{"id":"2103.02143","title":"Random Feature Attention","created":"2021-03-03","cited_by_count":354},{"id":"2201.05966","title":"UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models","created":"2022-01-16","cited_by_count":231},{"id":"2202.07922","title":"ZeroGen: Efficient Zero-shot Learning via Dataset Generation","created":"2022-02-16","cited_by_count":211},{"id":"2202.04538","title":"Generating Training Data with Language Models: Towards Zero-Shot Language Understanding","created":"2022-02-09","cited_by_count":199},{"id":"2104.07540","title":"Generating Datasets with Pretrained Language Models","created":"2021-04-15","cited_by_count":193},{"id":"2009.13845","title":"GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing","created":"2020-09-29","cited_by_count":171},{"id":"2104.08768","title":"Constrained Language Models Yield Few-Shot Semantic Parsers","created":"2021-04-18","cited_by_count":163},{"id":"2212.10375","title":"Self-Adaptive In-Context Learning: An Information Compression Perspective for In-Context Example Selection and Ordering","created":"2022-12-20","cited_by_count":161},{"id":"1904.09545","title":"Good-Enough Compositional Data Augmentation","created":"2019-04-21","cited_by_count":158},{"id":"2008.09335","title":"MTOP: A Comprehensive Multilingual Task-Oriented Semantic Parsing Benchmark","created":"2020-08-21","cited_by_count":158},{"id":"2201.11227","title":"Synchromesh: Reliable code generation from pre-trained language models","created":"2022-01-26","cited_by_count":156},{"id":"2302.05698","title":"Compositional Exemplars for In-context Learning","created":"2023-02-11","cited_by_count":144},{"id":"2001.11770","title":"Break It Down: A Question Understanding Benchmark","created":"2020-01-31","cited_by_count":131},{"id":"2010.02840","title":"Semantic Evaluation for Text-to-SQL with Distilled Test Suites","created":"2020-10-06","cited_by_count":126},{"id":"2204.11454","title":"Natural Language to Code Translation with Execution","created":"2022-04-25","cited_by_count":124},{"id":"1606.03622","title":"Data Recombination for Neural Semantic Parsing","created":"2016-06-11","cited_by_count":111},{"id":"1810.07942","title":"Semantic Parsing for Task Oriented Dialog using Hierarchical Representations","created":"2018-10-18","cited_by_count":101},{"id":"2204.00498","title":"Evaluating the Text-to-SQL Capabilities of Large Language Models","created":"2022-03-15","cited_by_count":101},{"id":"1704.08760","title":"Learning a Neural Semantic Parser from User Feedback","created":"2017-04-27","cited_by_count":99},{"id":"1802.08979","title":"NL2Bash: A Corpus and Semantic Parser for Natural Language Interface to the Linux Operating System","created":"2018-02-25","cited_by_count":98},{"id":"2207.14502","title":"Language Models Can Teach Themselves to Program Better","created":"2022-07-29","cited_by_count":78},{"id":"2009.07396","title":"Grounded Adaptation for Zero-shot Executable Semantic Parsing","created":"2020-09-16","cited_by_count":76},{"id":"1810.05237","title":"SyntaxSQLNet: Syntax Tree Networks for Complex and Cross-DomainText-to-SQL Task","created":"2018-10-11","cited_by_count":74},{"id":"2011.09039","title":"Sequence-Level Mixed Sample Data Augmentation","created":"2020-11-18","cited_by_count":71},{"id":"2210.12329","title":"ProGen: Progressive Zero-shot Dataset Generation via In-context Feedback","created":"2022-10-22","cited_by_count":67},{"id":"2010.03706","title":"Learning to Recombine and Resample Data for Compositional Generalization","created":"2020-10-08","cited_by_count":65},{"id":"2112.08696","title":"Few-Shot Semantic Parsing with Language Models Trained On Code","created":"2021-12-16","cited_by_count":50},{"id":"2205.12253","title":"Evaluating the Impact of Model Scale for Compositional Generalization in Semantic Parsing","created":"2022-05-24","cited_by_count":50},{"id":"2112.07610","title":"Improving Compositional Generalization with Latent Structure and Data Augmentation","created":"2021-12-14","cited_by_count":46},{"id":"2104.05827","title":"Learning to Synthesize Data for Semantic Parsing","created":"2021-04-12","cited_by_count":41},{"id":"2110.08458","title":"Controllable Semantic Parsing via Retrieval Augmentation","created":"2021-10-16","cited_by_count":35},{"id":"2010.11158","title":"Black-Box Ripper: Copying black-box models using generative evolutionary algorithms","created":"2020-10-21","cited_by_count":26},{"id":"1908.09940","title":"Don't paraphrase, detect! Rapid and Effective Data Collection for Semantic Parsing","created":"2019-08-26","cited_by_count":24},{"id":"2210.07074","title":"CLASP: Few-Shot Cross-Lingual Data Augmentation for Semantic Parsing","created":"2022-10-13","cited_by_count":21},{"id":"2012.04276","title":"Revisiting Iterative Back-Translation from the Perspective of Compositional Generalization","created":"2020-12-08","cited_by_count":19},{"id":"2106.06228","title":"From Paraphrasing to Semantic Parsing: Unsupervised Semantic Parsing via Synchronous Semantic Decoding","created":"2021-06-11","cited_by_count":14},{"id":"2104.08647","title":"Question Decomposition with Dependency Graphs","created":"2021-04-17","cited_by_count":7},{"id":"2205.08675","title":"Addressing Resource and Privacy Constraints in Semantic Parsing Through Data Augmentation","created":"2022-05-18","cited_by_count":7}],"next_cursor":null}