{"list":"other","total":53,"rows":[{"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":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"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":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"2103.07191","title":"Are NLP Models really able to Solve Simple Math Word Problems?","created":"2021-03-12","cited_by_count":878},{"id":"2204.07705","title":"Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks","created":"2022-04-16","cited_by_count":868},{"id":"2301.13688","title":"The Flan Collection: Designing Data and Methods for Effective Instruction Tuning","created":"2023-01-31","cited_by_count":739},{"id":"2104.08773","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","created":"2021-04-18","cited_by_count":699},{"id":"1709.00103","title":"Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning","created":"2017-08-31","cited_by_count":687},{"id":"1508.00305","title":"Compositional Semantic Parsing on Semi-Structured Tables","created":"2015-08-03","cited_by_count":515},{"id":"2110.15943","title":"MetaICL: Learning to Learn In Context","created":"2021-10-29","cited_by_count":454},{"id":"2004.02349","title":"TAPAS: Weakly Supervised Table Parsing via Pre-training","created":"2020-04-05","cited_by_count":434},{"id":"1909.02164","title":"TabFact: A Large-scale Dataset for Table-based Fact Verification","created":"2019-09-05","cited_by_count":428},{"id":"2005.08314","title":"TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data","created":"2020-05-17","cited_by_count":398},{"id":"2301.12726","title":"Specializing Smaller Language Models towards Multi-Step Reasoning","created":"2023-01-30","cited_by_count":251},{"id":"2107.07653","title":"TAPEX: Table Pre-training via Learning a Neural SQL Executor","created":"2021-07-16","cited_by_count":235},{"id":"2301.13808","title":"Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning","created":"2023-01-31","cited_by_count":178},{"id":"2009.13845","title":"GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing","created":"2020-09-29","cited_by_count":171},{"id":"2205.12393","title":"Fine-tuned Language Models are Continual Learners","created":"2022-05-24","cited_by_count":156},{"id":"2104.08835","title":"CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLP","created":"2021-04-18","cited_by_count":142},{"id":"2004.04487","title":"Injecting Numerical Reasoning Skills into Language Models","created":"2020-04-09","cited_by_count":133},{"id":"2210.06710","title":"Large Language Models are few(1)-shot Table Reasoners","created":"2022-10-13","cited_by_count":116},{"id":"1909.04849","title":"A Discrete Hard EM Approach for Weakly Supervised Question Answering","created":"2019-09-11","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":"2010.00571","title":"Understanding tables with intermediate pre-training","created":"2020-10-01","cited_by_count":68},{"id":"2010.11246","title":"On the Potential of Lexico-logical Alignments for Semantic Parsing to SQL Queries","created":"2020-10-21","cited_by_count":60},{"id":"1807.02322","title":"Memory Augmented Policy Optimization for Program Synthesis and Semantic Parsing","created":"2018-07-06","cited_by_count":57},{"id":"2201.11473","title":"Reasoning Like Program Executors","created":"2022-01-27","cited_by_count":45},{"id":"2211.02816","title":"PASTA: Table-Operations Aware Fact Verification via Sentence-Table Cloze Pre-training","created":"2022-11-05","cited_by_count":41},{"id":"1902.07198","title":"Learning to Generalize from Sparse and Underspecified Rewards","created":"2019-02-19","cited_by_count":39},{"id":"1511.04834","title":"Neural Programmer: Inducing Latent Programs with Gradient Descent","created":"2015-11-16","cited_by_count":34},{"id":"2302.14691","title":"Investigating the Effectiveness of Task-Agnostic Prefix Prompt for Instruction Following","created":"2023-02-28","cited_by_count":33},{"id":"2010.03084","title":"Program Enhanced Fact Verification with Verbalization and Graph Attention Network","created":"2020-10-06","cited_by_count":29},{"id":"2207.03637","title":"OmniTab: Pretraining with Natural and Synthetic Data for Few-shot Table-based Question Answering","created":"2022-07-08","cited_by_count":29},{"id":"1909.04165","title":"Learning Semantic Parsers from Denotations with Latent Structured Alignments and Abstract Programs","created":"2019-09-09","cited_by_count":26},{"id":"2004.13659","title":"LogicalFactChecker: Leveraging Logical Operations for Fact Checking with Graph Module Network","created":"2020-04-28","cited_by_count":26},{"id":"2206.10139","title":"Insights into Pre-training via Simpler Synthetic Tasks","created":"2022-06-21","cited_by_count":26},{"id":"1908.11787","title":"Answering Conversational Questions on Structured Data without Logical Forms","created":"2019-08-30","cited_by_count":24},{"id":"2205.12682","title":"TaCube: Pre-computing Data Cubes for Answering Numerical-Reasoning Questions over Tabular Data","created":"2022-05-25","cited_by_count":19},{"id":"1611.08945","title":"Learning a Natural Language Interface with Neural Programmer","created":"2016-11-28","cited_by_count":14},{"id":"2204.08753","title":"Table-based Fact Verification with Self-adaptive Mixture of Experts","created":"2022-04-19","cited_by_count":12},{"id":"1707.07806","title":"Macro Grammars and Holistic Triggering for Efficient Semantic Parsing","created":"2017-07-25","cited_by_count":10},{"id":"1710.01779","title":"Building a Web-Scale Dependency-Parsed Corpus from CommonCrawl","created":"2017-10-04","cited_by_count":9},{"id":"2205.12496","title":"Teaching Broad Reasoning Skills for Multi-Step QA by Generating Hard Contexts","created":"2022-05-25","cited_by_count":7},{"id":"1809.04271","title":"Knowledge-Aware Conversational Semantic Parsing Over Web Tables","created":"2018-09-12","cited_by_count":6},{"id":"2201.08081","title":"LEMON: Language-Based Environment Manipulation via Execution-Guided Pre-training","created":"2022-01-20","cited_by_count":5}],"next_cursor":null}