{"list":"other","total":67,"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":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"2012.14913","title":"Transformer Feed-Forward Layers Are Key-Value Memories","created":"2020-12-29","cited_by_count":1336},{"id":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"id":"2210.07229","title":"Mass-Editing Memory in a Transformer","created":"2022-10-13","cited_by_count":1001},{"id":"1911.12543","title":"How Can We Know What Language Models Know?","created":"2019-11-28","cited_by_count":959},{"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":"2002.12327","title":"A Primer in BERTology: What we know about how BERT works","created":"2020-02-27","cited_by_count":815},{"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":"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":"2104.08696","title":"Knowledge Neurons in Pretrained Transformers","created":"2021-04-18","cited_by_count":601},{"id":"2104.08164","title":"Editing Factual Knowledge in Language Models","created":"2021-04-16","cited_by_count":553},{"id":"2203.14680","title":"Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space","created":"2022-03-28","cited_by_count":532},{"id":"2304.14767","title":"Dissecting Recall of Factual Associations in Auto-Regressive Language Models","created":"2023-04-28","cited_by_count":528},{"id":"2306.11698","title":"DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models","created":"2023-06-20","cited_by_count":518},{"id":"2110.11309","title":"Fast Model Editing at Scale","created":"2021-10-21","cited_by_count":498},{"id":"2004.07667","title":"Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection","created":"2020-04-16","cited_by_count":455},{"id":"2206.06520","title":"Memory-Based Model Editing at Scale","created":"2022-06-13","cited_by_count":447},{"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":"1903.10561","title":"On Measuring Social Biases in Sentence Encoders","created":"2019-03-25","cited_by_count":398},{"id":"2103.00453","title":"Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP","created":"2021-02-28","cited_by_count":337},{"id":"2305.12740","title":"Can We Edit Factual Knowledge by In-Context Learning?","created":"2023-05-22","cited_by_count":285},{"id":"2211.11031","title":"Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors","created":"2022-11-20","cited_by_count":271},{"id":"2010.06032","title":"Measuring and Reducing Gendered Correlations in Pre-trained Models","created":"2020-10-12","cited_by_count":224},{"id":"1904.03310","title":"Gender Bias in Contextualized Word Embeddings","created":"2019-04-05","cited_by_count":203},{"id":"2105.04054","title":"Societal Biases in Language Generation: Progress and Challenges","created":"2021-05-10","cited_by_count":202},{"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":"2301.09785","title":"Transformer-Patcher: One Mistake worth One Neuron","created":"2023-01-24","cited_by_count":197},{"id":"2308.08742","title":"PMET: Precise Model Editing in a Transformer","created":"2023-08-17","cited_by_count":173},{"id":"2007.08100","title":"Towards Debiasing Sentence Representations","created":"2020-07-16","cited_by_count":171},{"id":"2004.00345","title":"Editable Neural Networks","created":"2020-04-01","cited_by_count":155},{"id":"2106.06087","title":"Causal Analysis of Syntactic Agreement Mechanisms in Neural Language Models","created":"2021-06-10","cited_by_count":131},{"id":"1912.03593","title":"Towards a Critical Race Methodology in Algorithmic Fairness","created":"2019-12-08","cited_by_count":125},{"id":"2004.11207","title":"Self-Attention Attribution: Interpreting Information Interactions Inside Transformer","created":"2020-04-23","cited_by_count":125},{"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":"2109.03646","title":"Sustainable Modular Debiasing of Language Models","created":"2021-09-08","cited_by_count":100},{"id":"2104.07143","title":"An Interpretability Illusion for BERT","created":"2021-04-14","cited_by_count":97},{"id":"2010.14534","title":"Unmasking Contextual Stereotypes: Measuring and Mitigating BERT's Gender Bias","created":"2020-10-27","cited_by_count":82},{"id":"2210.07700","title":"Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey","created":"2022-10-14","cited_by_count":80},{"id":"2111.13654","title":"Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefs","created":"2021-11-26","cited_by_count":79},{"id":"2103.06413","title":"FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoders","created":"2021-03-11","cited_by_count":75},{"id":"2310.12560","title":"Fast Model Debias with Machine Unlearning","created":"2023-10-19","cited_by_count":72},{"id":"2205.02526","title":"Theories of \"Gender\" in NLP Bias Research","created":"2022-05-05","cited_by_count":62},{"id":"2305.09941","title":"\"I'm fully who I am\": Towards Centering Transgender and Non-Binary Voices to Measure Biases in Open Language Generation","created":"2023-05-17","cited_by_count":56},{"id":"2305.12434","title":"BiasAsker: Measuring the Bias in Conversational AI System","created":"2023-05-21","cited_by_count":53},{"id":"2101.10001","title":"Diverse Adversaries for Mitigating Bias in Training","created":"2021-01-25","cited_by_count":48},{"id":"2211.03318","title":"Fixing Model Bugs with Natural Language Patches","created":"2022-11-07","cited_by_count":33},{"id":"2206.06423","title":"Hate Speech and Counter Speech Detection: Conversational Context Does Matter","created":"2022-06-13","cited_by_count":32},{"id":"2210.14975","title":"MABEL: Attenuating Gender Bias using Textual Entailment Data","created":"2022-10-26","cited_by_count":31},{"id":"2405.17814","title":"FAIntbench: A Holistic and Precise Benchmark for Bias Evaluation in Text-to-Image Models","created":"2024-05-28","cited_by_count":22},{"id":"2307.01595","title":"Prompt Tuning Pushes Farther, Contrastive Learning Pulls Closer: A Two-Stage Approach to Mitigate Social Biases","created":"2023-07-04","cited_by_count":21},{"id":"2407.10241","title":"BiasAlert: A Plug-and-play Tool for Social Bias Detection in LLMs","created":"2024-07-14","cited_by_count":21},{"id":"2405.09341","title":"Large Language Model Bias Mitigation from the Perspective of Knowledge Editing","created":"2024-05-15","cited_by_count":16},{"id":"2310.12490","title":"Co$^2$PT: Mitigating Bias in Pre-trained Language Models through Counterfactual Contrastive Prompt Tuning","created":"2023-10-19","cited_by_count":15},{"id":"2005.13630","title":"Explaining Neural Networks by Decoding Layer Activations","created":"2020-05-27","cited_by_count":13},{"id":"2307.08232","title":"Learning for Counterfactual Fairness from Observational Data","created":"2023-07-17","cited_by_count":13},{"id":"2210.11762","title":"Detecting Unintended Social Bias in Toxic Language Datasets","created":"2022-10-21","cited_by_count":12},{"id":"2212.11672","title":"Trustworthy Social Bias Measurement","created":"2022-12-20","cited_by_count":7}],"next_cursor":null}