{"list":"other","total":70,"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":"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"id":"1901.08746","title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","created":"2019-01-25","cited_by_count":1947},{"id":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"2007.14062","title":"Big Bird: Transformers for Longer Sequences","created":"2020-07-28","cited_by_count":1684},{"id":"1607.04606","title":"Enriching Word Vectors with Subword Information","created":"2016-07-15","cited_by_count":1583},{"id":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"id":"1903.10676","title":"SciBERT: A Pretrained Language Model for Scientific Text","created":"2019-03-26","cited_by_count":1414},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220},{"id":"2007.01282","title":"Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering","created":"2020-07-02","cited_by_count":1210},{"id":"1901.07291","title":"Cross-lingual Language Model Pretraining","created":"2019-01-22","cited_by_count":1090},{"id":"2005.04118","title":"Beyond Accuracy: Behavioral Testing of NLP models with CheckList","created":"2020-05-08","cited_by_count":1006},{"id":"1704.04683","title":"RACE: Large-scale ReAding Comprehension Dataset From Examinations","created":"2017-04-15","cited_by_count":861},{"id":"2002.12327","title":"A Primer in BERTology: What we know about how BERT works","created":"2020-02-27","cited_by_count":815},{"id":"1904.01766","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","created":"2019-04-03","cited_by_count":703},{"id":"1907.11932","title":"Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment","created":"2019-07-27","cited_by_count":671},{"id":"1911.12237","title":"SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization","created":"2019-11-27","cited_by_count":535},{"id":"2005.00700","title":"UnifiedQA: Crossing Format Boundaries With a Single QA System","created":"2020-05-02","cited_by_count":476},{"id":"1903.08855","title":"Linguistic Knowledge and Transferability of Contextual Representations","created":"2019-03-21","cited_by_count":383},{"id":"1808.05326","title":"SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference","created":"2018-08-16","cited_by_count":333},{"id":"1907.13528","title":"What BERT is not: Lessons from a new suite of psycholinguistic diagnostics for language models","created":"2019-07-31","cited_by_count":320},{"id":"1909.07606","title":"K-BERT: Enabling Language Representation with Knowledge Graph","created":"2019-09-17","cited_by_count":304},{"id":"2012.15409","title":"UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning","created":"2020-12-31","cited_by_count":239},{"id":"2102.01951","title":"Mind the Gap: Assessing Temporal Generalization in Neural Language Models","created":"2021-02-03","cited_by_count":230},{"id":"2202.01771","title":"Pre-Trained Language Models for Interactive Decision-Making","created":"2022-02-03","cited_by_count":221},{"id":"1909.07940","title":"Do NLP Models Know Numbers? Probing Numeracy in Embeddings","created":"2019-09-17","cited_by_count":159},{"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":"2004.14786","title":"Perturbed Masking: Parameter-free Probing for Analyzing and Interpreting BERT","created":"2020-04-30","cited_by_count":109},{"id":"2110.08529","title":"Sharpness-Aware Minimization Improves Language Model Generalization","created":"2021-10-16","cited_by_count":108},{"id":"2008.09036","title":"Language Models as Knowledge Bases: On Entity Representations, Storage Capacity, and Paraphrased Queries","created":"2020-08-20","cited_by_count":107},{"id":"2112.08313","title":"Measure and Improve Robustness in NLP Models: A Survey","created":"2021-12-15","cited_by_count":107},{"id":"1505.01257","title":"A Deeper Look at Dataset Bias","created":"2015-05-06","cited_by_count":87},{"id":"2109.05704","title":"Mitigating Language-Dependent Ethnic Bias in BERT","created":"2021-09-13","cited_by_count":87},{"id":"2208.11857","title":"Shortcut Learning of Large Language Models in Natural Language Understanding","created":"2022-08-25","cited_by_count":85},{"id":"2109.15290","title":"MatSciBERT: A Materials Domain Language Model for Text Mining and Information Extraction","created":"2021-09-30","cited_by_count":83},{"id":"1904.08398","title":"DocBERT: BERT for Document Classification","created":"2019-04-17","cited_by_count":68},{"id":"1908.08039","title":"\"Mask and Infill\" : Applying Masked Language Model to Sentiment Transfer","created":"2019-08-21","cited_by_count":48},{"id":"2007.06761","title":"Can neural networks acquire a structural bias from raw linguistic data?","created":"2020-07-14","cited_by_count":35},{"id":"2105.02987","title":"Do language models learn typicality judgments from text?","created":"2021-05-06","cited_by_count":32},{"id":"2001.01818","title":"Artificial Intelligence for Social Good: A Survey","created":"2020-01-07","cited_by_count":29},{"id":"1906.02124","title":"PatentBERT: Patent Classification with Fine-Tuning a pre-trained BERT Model","created":"2019-05-14","cited_by_count":24},{"id":"2206.15030","title":"Modern Question Answering Datasets and Benchmarks: A Survey","created":"2022-06-30","cited_by_count":23},{"id":"2007.06897","title":"What's in a Name? Are BERT Named Entity Representations just as Good for any other Name?","created":"2020-07-14","cited_by_count":17},{"id":"1904.04458","title":"Knowledge-Augmented Language Model and its Application to Unsupervised Named-Entity Recognition","created":"2019-04-09","cited_by_count":11},{"id":"2003.13027","title":"Abstractive Text Summarization based on Language Model Conditioning and Locality Modeling","created":"2020-03-29","cited_by_count":9},{"id":"2107.11275","title":"A Differentiable Language Model Adversarial Attack on Text Classifiers","created":"2021-07-23","cited_by_count":9},{"id":"2011.09159","title":"Do Fine-tuned Commonsense Language Models Really Generalize?","created":"2020-11-18","cited_by_count":8},{"id":"2004.10102","title":"Attention is Not Only a Weight: Analyzing Transformers with Vector Norms","created":"2020-04-21","cited_by_count":6},{"id":"2111.02603","title":"On Semantic Cognition, Inductive Generalization, and Language Models","created":"2021-11-04","cited_by_count":2},{"id":"2107.10935","title":"DeepTitle -- Leveraging BERT to generate Search Engine Optimized Headlines","created":"2021-07-22","cited_by_count":1}],"next_cursor":null}