{"list":"other","total":92,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"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":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"id":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"2004.10964","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","created":"2020-04-23","cited_by_count":1565},{"id":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"2206.14858","title":"Solving Quantitative Reasoning Problems with Language Models","created":"2022-06-29","cited_by_count":1392},{"id":"1803.05355","title":"FEVER: a large-scale dataset for Fact Extraction and VERification","created":"2018-03-14","cited_by_count":1375},{"id":"1808.08745","title":"Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization","created":"2018-08-27","cited_by_count":1317},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"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":"2104.08786","title":"Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity","created":"2021-04-18","cited_by_count":1135},{"id":"1805.12471","title":"Neural Network Acceptability Judgments","created":"2018-05-31","cited_by_count":958},{"id":"1903.00161","title":"DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs","created":"2019-03-01","cited_by_count":903},{"id":"1704.04683","title":"RACE: Large-scale ReAding Comprehension Dataset From Examinations","created":"2017-04-15","cited_by_count":861},{"id":"1910.14599","title":"Adversarial NLI: A New Benchmark for Natural Language Understanding","created":"2019-10-31","cited_by_count":807},{"id":"1707.06209","title":"Crowdsourcing Multiple Choice Science Questions","created":"2017-07-19","cited_by_count":765},{"id":"1703.04009","title":"Automated Hate Speech Detection and the Problem of Offensive Language","created":"2017-03-11","cited_by_count":736},{"id":"2010.00133","title":"CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models","created":"2020-09-30","cited_by_count":710},{"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":"1712.07040","title":"The NarrativeQA Reading Comprehension Challenge","created":"2017-12-19","cited_by_count":597},{"id":"1912.00582","title":"BLiMP: The Benchmark of Linguistic Minimal Pairs for English","created":"2019-12-02","cited_by_count":564},{"id":"2005.00700","title":"UnifiedQA: Crossing Format Boundaries With a Single QA System","created":"2020-05-02","cited_by_count":476},{"id":"2110.15943","title":"MetaICL: Learning to Learn In Context","created":"2021-10-29","cited_by_count":454},{"id":"1909.02164","title":"TabFact: A Large-scale Dataset for Table-based Fact Verification","created":"2019-09-05","cited_by_count":428},{"id":"1706.04115","title":"Zero-Shot Relation Extraction via Reading Comprehension","created":"2017-06-13","cited_by_count":426},{"id":"2010.12421","title":"TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classification","created":"2020-10-23","cited_by_count":417},{"id":"2012.10289","title":"HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection","created":"2020-12-18","cited_by_count":407},{"id":"1904.01130","title":"PAWS: Paraphrase Adversaries from Word Scrambling","created":"2019-04-01","cited_by_count":402},{"id":"1808.09121","title":"WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations","created":"2018-08-28","cited_by_count":372},{"id":"1705.00648","title":"\"Liar, Liar Pants on Fire\": A New Benchmark Dataset for Fake News Detection","created":"2017-05-01","cited_by_count":363},{"id":"2105.11447","title":"True Few-Shot Learning with Language Models","created":"2021-05-24","cited_by_count":344},{"id":"1808.05326","title":"SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference","created":"2018-08-16","cited_by_count":333},{"id":"1611.09830","title":"NewsQA: A Machine Comprehension Dataset","created":"2016-11-29","cited_by_count":331},{"id":"1307.5336","title":"Good Debt or Bad Debt: Detecting Semantic Orientations in Economic Texts","created":"2013-07-19","cited_by_count":310},{"id":"1908.05739","title":"Abductive Commonsense Reasoning","created":"2019-08-15","cited_by_count":301},{"id":"1909.00277","title":"Cosmos QA: Machine Reading Comprehension with Contextual Commonsense Reasoning","created":"2019-08-31","cited_by_count":285},{"id":"1910.11473","title":"QASC: A Dataset for Question Answering via Sentence Composition","created":"2019-10-25","cited_by_count":252},{"id":"1704.05179","title":"SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine","created":"2017-04-18","cited_by_count":225},{"id":"2010.09926","title":"Explainable Automated Fact-Checking for Public Health Claims","created":"2020-10-19","cited_by_count":211},{"id":"1810.12885","title":"ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension","created":"2018-10-30","cited_by_count":200},{"id":"1809.04444","title":"Hate Speech Dataset from a White Supremacy Forum","created":"2018-09-12","cited_by_count":198},{"id":"2103.08493","title":"How Many Data Points is a Prompt Worth?","created":"2021-03-15","cited_by_count":198},{"id":"2012.00614","title":"CLIMATE-FEVER: A Dataset for Verification of Real-World Climate Claims","created":"2020-12-01","cited_by_count":196},{"id":"2101.11038","title":"Muppet: Massive Multi-task Representations with Pre-Finetuning","created":"2021-01-26","cited_by_count":192},{"id":"2005.04611","title":"How Context Affects Language Models' Factual Predictions","created":"2020-05-10","cited_by_count":181},{"id":"2106.10328","title":"Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets","created":"2021-06-18","cited_by_count":181},{"id":"2110.07814","title":"Meta-learning via Language Model In-context Tuning","created":"2021-10-15","cited_by_count":164},{"id":"2111.10952","title":"ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning","created":"2021-11-22","cited_by_count":161},{"id":"1902.00164","title":"DREAM: A Challenge Dataset and Models for Dialogue-Based Reading Comprehension","created":"2019-02-01","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":"2005.00770","title":"Exploring and Predicting Transferability across NLP Tasks","created":"2020-05-02","cited_by_count":128},{"id":"2104.04670","title":"Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt Collections","created":"2021-04-10","cited_by_count":128},{"id":"1909.03065","title":"\"Going on a vacation\" takes longer than \"Going for a walk\": A Study of Temporal Commonsense Understanding","created":"2019-09-06","cited_by_count":123},{"id":"2005.00683","title":"Birds have four legs?! NumerSense: Probing Numerical Commonsense Knowledge of Pre-trained Language Models","created":"2020-05-02","cited_by_count":110},{"id":"1908.05803","title":"Quoref: A Reading Comprehension Dataset with Questions Requiring Coreferential Reasoning","created":"2019-08-16","cited_by_count":100},{"id":"1909.03553","title":"QuaRTz: An Open-Domain Dataset of Qualitative Relationship Questions","created":"2019-09-08","cited_by_count":89},{"id":"2204.13509","title":"On the Effect of Pretraining Corpora on In-context Learning by a Large-scale Language Model","created":"2022-04-28","cited_by_count":81},{"id":"1908.05852","title":"Reasoning Over Paragraph Effects in Situations","created":"2019-08-16","cited_by_count":79},{"id":"1909.04739","title":"WIQA: A dataset for \"What if...\" reasoning over procedural text","created":"2019-09-10","cited_by_count":71},{"id":"2107.07170","title":"FLEX: Unifying Evaluation for Few-Shot NLP","created":"2021-07-15","cited_by_count":67},{"id":"2107.06955","title":"HTLM: Hyper-Text Pre-Training and Prompting of Language Models","created":"2021-07-14","cited_by_count":58},{"id":"2205.01703","title":"Improving In-Context Few-Shot Learning via Self-Supervised Training","created":"2022-05-03","cited_by_count":57},{"id":"1907.06292","title":"TWEETQA: A Social Media Focused Question Answering Dataset","created":"2019-07-14","cited_by_count":55},{"id":"2201.06910","title":"ZeroPrompt: Scaling Prompt-Based Pretraining to 1,000 Tasks Improves Zero-Shot Generalization","created":"2022-01-18","cited_by_count":54},{"id":"2008.13546","title":"Effective Transfer Learning for Identifying Similar Questions: Matching User Questions to COVID-19 FAQs","created":"2020-08-04","cited_by_count":48},{"id":"2011.02686","title":"Investigating Societal Biases in a Poetry Composition System","created":"2020-11-05","cited_by_count":48},{"id":"1811.08048","title":"QuaRel: A Dataset and Models for Answering Questions about Qualitative Relationships","created":"2018-11-20","cited_by_count":46},{"id":"2005.00771","title":"ProtoQA: A Question Answering Dataset for Prototypical Common-Sense Reasoning","created":"2020-05-02","cited_by_count":46},{"id":"2107.07261","title":"Turning Tables: Generating Examples from Semi-structured Tables for Endowing Language Models with Reasoning Skills","created":"2021-07-15","cited_by_count":39},{"id":"2010.03450","title":"\"I'd rather just go to bed\": Understanding Indirect Answers","created":"2020-10-07","cited_by_count":36},{"id":"2005.06376","title":"BIOMRC: A Dataset for Biomedical Machine Reading Comprehension","created":"2020-05-13","cited_by_count":35},{"id":"1903.11850","title":"Mining Discourse Markers for Unsupervised Sentence Representation Learning","created":"2019-03-28","cited_by_count":34},{"id":"1808.09419","title":"Identifying Well-formed Natural Language Questions","created":"2018-08-28","cited_by_count":29},{"id":"2204.11117","title":"Exploring the Role of Task Transferability in Large-Scale Multi-Task Learning","created":"2022-04-23","cited_by_count":17},{"id":"2110.07731","title":"CCQA: A New Web-Scale Question Answering Dataset for Model Pre-Training","created":"2021-10-14","cited_by_count":13}],"next_cursor":null}