{"list":"other","total":71,"rows":[{"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":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"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":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"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":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"1906.02243","title":"Energy and Policy Considerations for Deep Learning in NLP","created":"2019-06-05","cited_by_count":1254},{"id":"1810.03993","title":"Model Cards for Model Reporting","created":"2018-10-05","cited_by_count":1080},{"id":"1809.05053","title":"XNLI: Evaluating Cross-lingual Sentence Representations","created":"2018-09-13","cited_by_count":915},{"id":"2004.09095","title":"The State and Fate of Linguistic Diversity and Inclusion in the NLP World","created":"2020-04-20","cited_by_count":798},{"id":"2003.11080","title":"XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization","created":"2020-03-24","cited_by_count":742},{"id":"1906.01502","title":"How multilingual is Multilingual BERT?","created":"2019-06-04","cited_by_count":645},{"id":"1910.11856","title":"On the Cross-lingual Transferability of Monolingual Representations","created":"2019-10-25","cited_by_count":578},{"id":"2104.10350","title":"Carbon Emissions and Large Neural Network Training","created":"2021-04-21","cited_by_count":567},{"id":"2003.05002","title":"TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages","created":"2020-03-10","cited_by_count":488},{"id":"2306.16388","title":"Towards Measuring the Representation of Subjective Global Opinions in Language Models","created":"2023-06-28","cited_by_count":437},{"id":"1812.10464","title":"Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond","created":"2018-12-26","cited_by_count":434},{"id":"2111.15366","title":"AI and the Everything in the Whole Wide World Benchmark","created":"2021-11-26","cited_by_count":349},{"id":"1910.07475","title":"MLQA: Evaluating Cross-lingual Extractive Question Answering","created":"2019-10-16","cited_by_count":340},{"id":"2005.00333","title":"XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning","created":"2020-05-01","cited_by_count":333},{"id":"1908.11828","title":"PAWS-X: A Cross-lingual Adversarial Dataset for Paraphrase Identification","created":"2019-08-30","cited_by_count":264},{"id":"2002.05651","title":"Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning","created":"2020-01-31","cited_by_count":249},{"id":"2006.16923","title":"Large image datasets: A pyrrhic win for computer vision?","created":"2020-06-24","cited_by_count":237},{"id":"1905.12516","title":"Racial Bias in Hate Speech and Abusive Language Detection Datasets","created":"2019-05-29","cited_by_count":209},{"id":"2305.18189","title":"Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models","created":"2023-05-29","cited_by_count":207},{"id":"2212.08061","title":"On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning","created":"2022-12-15","cited_by_count":194},{"id":"2305.13707","title":"Do All Languages Cost the Same? Tokenization in the Era of Commercial Language Models","created":"2023-05-23","cited_by_count":192},{"id":"2106.15590","title":"The Values Encoded in Machine Learning Research","created":"2021-06-29","cited_by_count":172},{"id":"2104.07412","title":"XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation","created":"2021-04-15","cited_by_count":168},{"id":"2202.05924","title":"Compute Trends Across Three Eras of Machine Learning","created":"2022-02-11","cited_by_count":163},{"id":"2009.06489","title":"The Hardware Lottery","created":"2020-09-14","cited_by_count":160},{"id":"2010.02353","title":"Participatory Research for Low-resourced Machine Translation: A Case Study in African Languages","created":"2020-10-05","cited_by_count":159},{"id":"2008.09335","title":"MTOP: A Comprehensive Multilingual Task-Oriented Semantic Parsing Benchmark","created":"2020-08-21","cited_by_count":158},{"id":"2103.11811","title":"MasakhaNER: Named Entity Recognition for African Languages","created":"2021-03-22","cited_by_count":155},{"id":"2203.13722","title":"Probing Pre-Trained Language Models for Cross-Cultural Differences in Values","created":"2022-03-25","cited_by_count":149},{"id":"2204.08582","title":"MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages","created":"2022-04-18","cited_by_count":146},{"id":"2209.07572","title":"Power to the People? Opportunities and Challenges for Participatory AI","created":"2022-09-15","cited_by_count":138},{"id":"2010.11856","title":"XOR QA: Cross-lingual Open-Retrieval Question Answering","created":"2020-10-22","cited_by_count":121},{"id":"2007.04068","title":"Decolonial AI: Decolonial Theory as Sociotechnical Foresight in Artificial Intelligence","created":"2020-07-08","cited_by_count":101},{"id":"2205.02022","title":"A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translation","created":"2022-05-04","cited_by_count":98},{"id":"2004.04721","title":"Translation Artifacts in Cross-lingual Transfer Learning","created":"2020-04-09","cited_by_count":96},{"id":"2310.16787","title":"The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AI","created":"2023-10-25","cited_by_count":73},{"id":"1707.00061","title":"Racial Disparity in Natural Language Processing: A Case Study of Social Media African-American English","created":"2017-06-30","cited_by_count":71},{"id":"2203.13357","title":"One Country, 700+ Languages: NLP Challenges for Underrepresented Languages and Dialects in Indonesia","created":"2022-03-24","cited_by_count":66},{"id":"2010.02510","title":"Investigating African-American Vernacular English in Transformer-Based Text Generation","created":"2020-10-06","cited_by_count":53},{"id":"2104.10097","title":"Beyond Fair Pay: Ethical Implications of NLP Crowdsourcing","created":"2021-04-20","cited_by_count":53},{"id":"2212.08011","title":"Multi-VALUE: A Framework for Cross-Dialectal English NLP","created":"2022-12-15","cited_by_count":53},{"id":"2003.11529","title":"Masakhane -- Machine Translation For Africa","created":"2020-03-13","cited_by_count":49},{"id":"2110.03036","title":"The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation","created":"2021-10-06","cited_by_count":47},{"id":"2204.03031","title":"VALUE: Understanding Dialect Disparity in NLU","created":"2022-04-06","cited_by_count":47},{"id":"2306.03090","title":"Is ChatGPT a Good Teacher Coach? Measuring Zero-Shot Performance For Scoring and Providing Actionable Insights on Classroom Instruction","created":"2023-06-05","cited_by_count":37},{"id":"2011.05402","title":"OCR Post Correction for Endangered Language Texts","created":"2020-11-10","cited_by_count":31},{"id":"1806.04291","title":"Challenges of language technologies for the indigenous languages of the Americas","created":"2018-06-12","cited_by_count":29},{"id":"2212.10168","title":"Naamapadam: A Large-Scale Named Entity Annotated Data for Indic Languages","created":"2022-12-20","cited_by_count":28},{"id":"2206.00437","title":"What a Creole Wants, What a Creole Needs","created":"2022-06-01","cited_by_count":27},{"id":"2305.19474","title":"Ethical Considerations for Machine Translation of Indigenous Languages: Giving a Voice to the Speakers","created":"2023-05-31","cited_by_count":27},{"id":"2112.03497","title":"Dataset Geography: Mapping Language Data to Language Users","created":"2021-12-07","cited_by_count":22},{"id":"2109.13137","title":"Mitigating Racial Biases in Toxic Language Detection with an Equity-Based Ensemble Framework","created":"2021-09-27","cited_by_count":19},{"id":"2210.14424","title":"Geographic Citation Gaps in NLP Research","created":"2022-10-26","cited_by_count":19},{"id":"2109.06074","title":"On Language Models for Creoles","created":"2021-09-13","cited_by_count":17},{"id":"2305.14996","title":"The ACL OCL Corpus: Advancing Open Science in Computational Linguistics","created":"2023-05-24","cited_by_count":17},{"id":"1306.6755","title":"Arabizi Detection and Conversion to Arabic","created":"2013-06-28","cited_by_count":16},{"id":"2212.03419","title":"JamPatoisNLI: A Jamaican Patois Natural Language Inference Dataset","created":"2022-12-07","cited_by_count":11},{"id":"1912.01218","title":"Writing Across the World's Languages: Deep Internationalization for Gboard, the Google Keyboard","created":"2019-12-03","cited_by_count":10},{"id":"2303.17972","title":"$\\varepsilon$ K\\'U <MASK>: Integrating Yor\\`ub\\'a cultural greetings into machine translation","created":"2023-03-31","cited_by_count":8},{"id":"2303.16828","title":"Tackling Hate Speech in Low-resource Languages with Context Experts","created":"2023-03-29","cited_by_count":7},{"id":"2308.08656","title":"Flickr Africa: Examining Geo-Diversity in Large-Scale, Human-Centric Visual Data","created":"2023-08-16","cited_by_count":5}],"next_cursor":null}