{"list":"other","total":55,"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":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"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":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"1607.06520","title":"Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings","created":"2016-07-21","cited_by_count":1312},{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026},{"id":"2005.14050","title":"Language (Technology) is Power: A Critical Survey of \"Bias\" in NLP","created":"2020-05-28","cited_by_count":956},{"id":"2004.09456","title":"StereoSet: Measuring stereotypical bias in pretrained language models","created":"2020-04-20","cited_by_count":924},{"id":"1608.07187","title":"Semantics derived automatically from language corpora contain human-like biases","created":"2016-08-25","cited_by_count":901},{"id":"2306.01116","title":"The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only","created":"2023-06-01","cited_by_count":763},{"id":"2209.07858","title":"Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned","created":"2022-08-23","cited_by_count":729},{"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":"2110.08193","title":"BBQ: A Hand-Built Bias Benchmark for Question Answering","created":"2021-10-15","cited_by_count":701},{"id":"1804.06876","title":"Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods","created":"2018-04-18","cited_by_count":659},{"id":"1804.09301","title":"Gender Bias in Coreference Resolution","created":"2018-04-25","cited_by_count":442},{"id":"1706.04115","title":"Zero-Shot Relation Extraction via Reading Comprehension","created":"2017-06-13","cited_by_count":426},{"id":"2012.10289","title":"HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection","created":"2020-12-18","cited_by_count":407},{"id":"1502.05698","title":"Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks","created":"2015-02-19","cited_by_count":314},{"id":"1906.07337","title":"Measuring Bias in Contextualized Word Representations","created":"2019-06-18","cited_by_count":276},{"id":"1906.00591","title":"Evaluating Gender Bias in Machine Translation","created":"2019-06-03","cited_by_count":249},{"id":"1805.04508","title":"Examining Gender and Race Bias in Two Hundred Sentiment Analysis Systems","created":"2018-05-11","cited_by_count":234},{"id":"2010.06032","title":"Measuring and Reducing Gendered Correlations in Pre-trained Models","created":"2020-10-12","cited_by_count":224},{"id":"1808.06640","title":"Adversarial Removal of Demographic Attributes from Text Data","created":"2018-08-20","cited_by_count":170},{"id":"2205.09209","title":"\"I'm sorry to hear that\": Finding New Biases in Language Models with a Holistic Descriptor Dataset","created":"2022-05-18","cited_by_count":162},{"id":"1911.03064","title":"Reducing Sentiment Bias in Language Models via Counterfactual Evaluation","created":"2019-11-08","cited_by_count":148},{"id":"2012.15859","title":"Intrinsic Bias Metrics Do Not Correlate with Application Bias","created":"2020-12-31","cited_by_count":148},{"id":"1911.01485","title":"Assessing Social and Intersectional Biases in Contextualized Word Representations","created":"2019-11-04","cited_by_count":135},{"id":"2010.02428","title":"UnQovering Stereotyping Biases via Underspecified Questions","created":"2020-10-06","cited_by_count":126},{"id":"1908.09369","title":"On Measuring and Mitigating Biased Inferences of Word Embeddings","created":"2019-08-25","cited_by_count":112},{"id":"2109.05704","title":"Mitigating Language-Dependent Ethnic Bias in BERT","created":"2021-09-13","cited_by_count":87},{"id":"2106.14574","title":"Quantifying Social Biases in NLP: A Generalization and Empirical Comparison of Extrinsic Fairness Metrics","created":"2021-06-28","cited_by_count":83},{"id":"2010.14534","title":"Unmasking Contextual Stereotypes: Measuring and Mitigating BERT's Gender Bias","created":"2020-10-27","cited_by_count":82},{"id":"1910.04210","title":"Perturbation Sensitivity Analysis to Detect Unintended Model Biases","created":"2019-10-09","cited_by_count":74},{"id":"1804.07927","title":"DuoRC: Towards Complex Language Understanding with Paraphrased Reading Comprehension","created":"2018-04-21","cited_by_count":71},{"id":"1901.07656","title":"Attenuating Bias in Word Vectors","created":"2019-01-23","cited_by_count":64},{"id":"1905.11684","title":"On Measuring Gender Bias in Translation of Gender-neutral Pronouns","created":"2019-05-28","cited_by_count":60},{"id":"1907.06292","title":"TWEETQA: A Social Media Focused Question Answering Dataset","created":"2019-07-14","cited_by_count":55},{"id":"2210.04337","title":"Quantifying Social Biases Using Templates is Unreliable","created":"2022-10-09","cited_by_count":39},{"id":"2204.02285","title":"SwapMix: Diagnosing and Regularizing the Over-Reliance on Visual Context in Visual Question Answering","created":"2022-04-05","cited_by_count":38},{"id":"2305.11242","title":"Comparing Biases and the Impact of Multilingual Training across Multiple Languages","created":"2023-05-18","cited_by_count":36},{"id":"2210.10040","title":"The Tail Wagging the Dog: Dataset Construction Biases of Social Bias Benchmarks","created":"2022-10-18","cited_by_count":31},{"id":"1803.05223","title":"MCScript: A Novel Dataset for Assessing Machine Comprehension Using Script Knowledge","created":"2018-03-14","cited_by_count":30},{"id":"2210.07269","title":"SODAPOP: Open-Ended Discovery of Social Biases in Social Commonsense Reasoning Models","created":"2022-10-13","cited_by_count":22},{"id":"1711.05885","title":"Crowdsourcing Question-Answer Meaning Representations","created":"2017-11-16","cited_by_count":21},{"id":"2307.09209","title":"Automated Ableism: An Exploration of Explicit Disability Biases in Sentiment and Toxicity Analysis Models","created":"2023-07-18","cited_by_count":20},{"id":"1906.10256","title":"Good Secretaries, Bad Truck Drivers? Occupational Gender Stereotypes in Sentiment Analysis","created":"2019-06-24","cited_by_count":19},{"id":"2205.06303","title":"Using Natural Sentences for Understanding Biases in Language Models","created":"2022-05-12","cited_by_count":19},{"id":"2302.01448","title":"Out of Context: Investigating the Bias and Fairness Concerns of \"Artificial Intelligence as a Service\"","created":"2023-02-02","cited_by_count":15},{"id":"2111.13259","title":"Identification of Bias Against People with Disabilities in Sentiment Analysis and Toxicity Detection Models","created":"2021-11-25","cited_by_count":13}],"next_cursor":null}