{"list":"other","total":52,"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":"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":"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":"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":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"1804.08771","title":"A Call for Clarity in Reporting BLEU Scores","created":"2018-04-23","cited_by_count":1799},{"id":"2111.09543","title":"DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing","created":"2021-11-18","cited_by_count":1254},{"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":"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":"2305.09645","title":"StructGPT: A General Framework for Large Language Model to Reason over Structured Data","created":"2023-05-16","cited_by_count":343},{"id":"2004.14373","title":"ToTTo: A Controlled Table-To-Text Generation Dataset","created":"2020-04-29","cited_by_count":268},{"id":"2302.08468","title":"LEVER: Learning to Verify Language-to-Code Generation with Execution","created":"2023-02-16","cited_by_count":239},{"id":"2107.07653","title":"TAPEX: Table Pre-training via Learning a Neural SQL Executor","created":"2021-07-16","cited_by_count":235},{"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":"2210.02875","title":"Binding Language Models in Symbolic Languages","created":"2022-10-06","cited_by_count":228},{"id":"2210.03849","title":"ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answering","created":"2022-10-07","cited_by_count":196},{"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":"2104.00369","title":"FeTaQA: Free-form Table Question Answering","created":"2021-04-01","cited_by_count":175},{"id":"2009.13845","title":"GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing","created":"2020-09-29","cited_by_count":171},{"id":"1703.01488","title":"Autoencoding Variational Inference For Topic Models","created":"2017-03-04","cited_by_count":169},{"id":"2106.05707","title":"FEVEROUS: Fact Extraction and VERification Over Unstructured and Structured information","created":"2021-06-10","cited_by_count":167},{"id":"2007.02871","title":"DART: Open-Domain Structured Data Record to Text Generation","created":"2020-07-06","cited_by_count":145},{"id":"2108.06712","title":"HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generation","created":"2021-08-15","cited_by_count":118},{"id":"2210.06710","title":"Large Language Models are few(1)-shot Table Reasoners","created":"2022-10-13","cited_by_count":116},{"id":"2203.00274","title":"TableFormer: Robust Transformer Modeling for Table-Text Encoding","created":"2022-03-01","cited_by_count":91},{"id":"2004.10404","title":"Logical Natural Language Generation from Open-Domain Tables","created":"2020-04-22","cited_by_count":90},{"id":"1911.04118","title":"TANDA: Transfer and Adapt Pre-Trained Transformer Models for Answer Sentence Selection","created":"2019-11-11","cited_by_count":74},{"id":"2010.00571","title":"Understanding tables with intermediate pre-training","created":"2020-10-01","cited_by_count":68},{"id":"2109.04312","title":"MATE: Multi-view Attention for Table Transformer Efficiency","created":"2021-09-09","cited_by_count":54},{"id":"2004.14579","title":"Logic2Text: High-Fidelity Natural Language Generation from Logical Forms","created":"2020-04-30","cited_by_count":45},{"id":"2306.14321","title":"RobuT: A Systematic Study of Table QA Robustness Against Human-Annotated Adversarial Perturbations","created":"2023-06-25","cited_by_count":43},{"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":"2105.13995","title":"SemEval-2021 Task 9: Fact Verification and Evidence Finding for Tabular Data in Scientific Documents (SEM-TAB-FACTS)","created":"2021-05-28","cited_by_count":35},{"id":"2210.12374","title":"ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples","created":"2022-10-22","cited_by_count":29},{"id":"2204.13243","title":"HybriDialogue: An Information-Seeking Dialogue Dataset Grounded on Tabular and Textual Data","created":"2022-04-28","cited_by_count":28},{"id":"2212.09994","title":"Towards Robustness of Text-to-SQL Models Against Natural and Realistic Adversarial Table Perturbation","created":"2022-12-20","cited_by_count":28},{"id":"2104.04243","title":"Incorporating External Knowledge to Enhance Tabular Reasoning","created":"2021-04-09","cited_by_count":23},{"id":"2305.11725","title":"S$^3$HQA: A Three-Stage Approach for Multi-hop Text-Table Hybrid Question Answering","created":"2023-05-19","cited_by_count":17},{"id":"2107.04217","title":"Joint Models for Answer Verification in Question Answering Systems","created":"2021-07-09","cited_by_count":13},{"id":"2112.07337","title":"Multi-Row, Multi-Span Distant Supervision For Table+Text Question","created":"2021-12-14","cited_by_count":12},{"id":"2204.03357","title":"Parameter-Efficient Abstractive Question Answering over Tables or Text","created":"2022-04-07","cited_by_count":11},{"id":"2210.10350","title":"MuGER$^2$: Multi-Granularity Evidence Retrieval and Reasoning for Hybrid Question Answering","created":"2022-10-19","cited_by_count":9},{"id":"2106.00479","title":"DoT: An efficient Double Transformer for NLP tasks with tables","created":"2021-06-01","cited_by_count":8},{"id":"2212.02691","title":"LUNA: Language Understanding with Number Augmentations on Transformers via Number Plugins and Pre-training","created":"2022-12-06","cited_by_count":8},{"id":"2203.03549","title":"Question-Answer Sentence Graph for Joint Modeling Answer Selection","created":"2022-02-16","cited_by_count":6}],"next_cursor":null}