{"list":"other","total":61,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"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":"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":"1704.04683","title":"RACE: Large-scale ReAding Comprehension Dataset From Examinations","created":"2017-04-15","cited_by_count":861},{"id":"2008.08186","title":"Prevalence of Neural Collapse during the terminal phase of deep learning training","created":"2020-08-18","cited_by_count":719},{"id":"1804.06876","title":"Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods","created":"2018-04-18","cited_by_count":659},{"id":"2309.00770","title":"Bias and Fairness in Large Language Models: A Survey","created":"2023-09-02","cited_by_count":639},{"id":"2004.07667","title":"Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection","created":"2020-04-16","cited_by_count":455},{"id":"2305.07759","title":"TinyStories: How Small Can Language Models Be and Still Speak Coherent English?","created":"2023-05-12","cited_by_count":449},{"id":"1903.10561","title":"On Measuring Social Biases in Sentence Encoders","created":"2019-03-25","cited_by_count":398},{"id":"1901.09451","title":"Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting","created":"2019-01-27","cited_by_count":349},{"id":"2010.06032","title":"Measuring and Reducing Gendered Correlations in Pre-trained Models","created":"2020-10-12","cited_by_count":224},{"id":"1807.11714","title":"Gender Bias in Neural Natural Language Processing","created":"2018-07-31","cited_by_count":211},{"id":"1904.03310","title":"Gender Bias in Contextualized Word Embeddings","created":"2019-04-05","cited_by_count":203},{"id":"1906.04571","title":"Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology","created":"2019-06-11","cited_by_count":200},{"id":"2007.08100","title":"Towards Debiasing Sentence Representations","created":"2020-07-16","cited_by_count":171},{"id":"2006.03955","title":"Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases","created":"2020-06-06","cited_by_count":167},{"id":"2101.12699","title":"Exploring Deep Neural Networks via Layer-Peeled Model: Minority Collapse in Imbalanced Training","created":"2021-01-29","cited_by_count":166},{"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":"2106.02073","title":"Neural Collapse Under MSE Loss: Proximity to and Dynamics on the Central Path","created":"2021-06-03","cited_by_count":158},{"id":"1809.10610","title":"Counterfactual Fairness in Text Classification through Robustness","created":"2018-09-27","cited_by_count":151},{"id":"1911.03064","title":"Reducing Sentiment Bias in Language Models via Counterfactual Evaluation","created":"2019-11-08","cited_by_count":148},{"id":"1904.04047","title":"Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddings","created":"2019-04-03","cited_by_count":147},{"id":"2312.03689","title":"Evaluating and Mitigating Discrimination in Language Model Decisions","created":"2023-12-06","cited_by_count":124},{"id":"1908.09369","title":"On Measuring and Mitigating Biased Inferences of Word Embeddings","created":"2019-08-25","cited_by_count":112},{"id":"2101.09523","title":"Debiasing Pre-trained Contextualised Embeddings","created":"2021-01-23","cited_by_count":107},{"id":"1909.00871","title":"It's All in the Name: Mitigating Gender Bias with Name-Based Counterfactual Data Substitution","created":"2019-09-02","cited_by_count":103},{"id":"2201.12091","title":"Linear Adversarial Concept Erasure","created":"2022-01-28","cited_by_count":101},{"id":"2112.15121","title":"On the Role of Neural Collapse in Transfer Learning","created":"2021-12-30","cited_by_count":100},{"id":"2203.09081","title":"Inducing Neural Collapse in Imbalanced Learning: Do We Really Need a Learnable Classifier at the End of Deep Neural Network?","created":"2022-03-17","cited_by_count":100},{"id":"2203.01238","title":"On the Optimization Landscape of Neural Collapse under MSE Loss: Global Optimality with Unconstrained Features","created":"2022-03-02","cited_by_count":97},{"id":"2308.10149","title":"A Survey on Fairness in Large Language Models","created":"2023-08-20","cited_by_count":95},{"id":"2010.14534","title":"Unmasking Contextual Stereotypes: Measuring and Mitigating BERT's Gender Bias","created":"2020-10-27","cited_by_count":82},{"id":"2210.02192","title":"Are All Losses Created Equal: A Neural Collapse Perspective","created":"2022-10-04","cited_by_count":78},{"id":"2103.06413","title":"FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoders","created":"2021-03-11","cited_by_count":75},{"id":"2202.08384","title":"Limitations of Neural Collapse for Understanding Generalization in Deep Learning","created":"2022-02-17","cited_by_count":63},{"id":"2109.03858","title":"Collecting a Large-Scale Gender Bias Dataset for Coreference Resolution and Machine Translation","created":"2021-09-08","cited_by_count":62},{"id":"2303.10058","title":"No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifier","created":"2023-03-17","cited_by_count":55},{"id":"2205.12586","title":"Perturbation Augmentation for Fairer NLP","created":"2022-05-25","cited_by_count":52},{"id":"2101.10001","title":"Diverse Adversaries for Mitigating Bias in Training","created":"2021-01-25","cited_by_count":48},{"id":"2405.17767","title":"Linguistic Collapse: Neural Collapse in (Large) Language Models","created":"2024-05-28","cited_by_count":38},{"id":"2210.17020","title":"A Law of Data Separation in Deep Learning","created":"2022-10-31","cited_by_count":36},{"id":"2110.05367","title":"Improving Gender Fairness of Pre-Trained Language Models without Catastrophic Forgetting","created":"2021-10-11","cited_by_count":35},{"id":"2109.10645","title":"Contrastive Learning for Fair Representations","created":"2021-09-22","cited_by_count":34},{"id":"2311.01479","title":"Detecting Out-of-Distribution Through the Lens of Neural Collapse","created":"2023-11-02","cited_by_count":34},{"id":"2210.14975","title":"MABEL: Attenuating Gender Bias using Textual Entailment Data","created":"2022-10-26","cited_by_count":31},{"id":"2211.05414","title":"ADEPT: A DEbiasing PrompT Framework","created":"2022-11-10","cited_by_count":21},{"id":"2106.10826","title":"Does Robustness Improve Fairness? Approaching Fairness with Word Substitution Robustness Methods for Text Classification","created":"2021-06-21","cited_by_count":20},{"id":"2405.05587","title":"Navigate Beyond Shortcuts: Debiased Learning through the Lens of Neural Collapse","created":"2024-05-09","cited_by_count":13},{"id":"2405.08920","title":"Neural Collapse Meets Differential Privacy: Curious Behaviors of NoisyGD with Near-perfect Representation Learning","created":"2024-05-14","cited_by_count":8},{"id":"2310.08358","title":"Towards Demystifying the Generalization Behaviors When Neural Collapse Emerges","created":"2023-10-12","cited_by_count":7},{"id":"2202.06467","title":"NeuroMixGDP: A Neural Collapse-Inspired Random Mixup for Private Data Release","created":"2022-02-14","cited_by_count":2}],"next_cursor":null}