{"list":"other","total":59,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"id":"1706.03825","title":"SmoothGrad: removing noise by adding noise","created":"2017-06-12","cited_by_count":1109},{"id":"1506.06724","title":"Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books","created":"2015-06-22","cited_by_count":1043},{"id":"1902.10186","title":"Attention is not Explanation","created":"2019-02-26","cited_by_count":929},{"id":"2005.00928","title":"Quantifying Attention Flow in Transformers","created":"2020-05-02","cited_by_count":775},{"id":"1804.06876","title":"Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods","created":"2018-04-18","cited_by_count":659},{"id":"1609.05807","title":"Inherent Trade-Offs in the Fair Determination of Risk Scores","created":"2016-09-19","cited_by_count":586},{"id":"2004.07667","title":"Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection","created":"2020-04-16","cited_by_count":455},{"id":"1906.03731","title":"Is Attention Interpretable?","created":"2019-06-09","cited_by_count":389},{"id":"2205.15480","title":"Post-hoc Concept Bottleneck Models","created":"2022-05-31","cited_by_count":293},{"id":"1606.04155","title":"Rationalizing Neural Predictions","created":"2016-06-13","cited_by_count":281},{"id":"1903.03862","title":"Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them","created":"2019-03-09","cited_by_count":268},{"id":"2306.03819","title":"LEACE: Perfect linear concept erasure in closed form","created":"2023-06-06","cited_by_count":267},{"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":"1806.02847","title":"A Simple Method for Commonsense Reasoning","created":"2018-06-07","cited_by_count":223},{"id":"2101.00288","title":"Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models","created":"2021-01-01","cited_by_count":222},{"id":"1606.05386","title":"Model-Agnostic Interpretability of Machine Learning","created":"2016-06-16","cited_by_count":219},{"id":"2005.01831","title":"Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?","created":"2020-05-04","cited_by_count":190},{"id":"2007.08100","title":"Towards Debiasing Sentence Representations","created":"2020-07-16","cited_by_count":171},{"id":"1809.01496","title":"Learning Gender-Neutral Word Embeddings","created":"2018-08-29","cited_by_count":169},{"id":"1808.07231","title":"Reducing Gender Bias in Abusive Language Detection","created":"2018-08-22","cited_by_count":152},{"id":"1804.05392","title":"Higher-order Coreference Resolution with Coarse-to-fine Inference","created":"2018-04-15","cited_by_count":150},{"id":"1905.08160","title":"Interpretable Neural Predictions with Differentiable Binary Variables","created":"2019-05-20","cited_by_count":126},{"id":"2207.07068","title":"Bias Mitigation for Machine Learning Classifiers: A Comprehensive Survey","created":"2022-07-14","cited_by_count":125},{"id":"2104.06001","title":"Gender Bias in Machine Translation","created":"2021-04-13","cited_by_count":117},{"id":"1908.04211","title":"On Identifiability in Transformers","created":"2019-08-12","cited_by_count":116},{"id":"2005.00115","title":"Learning to Faithfully Rationalize by Construction","created":"2020-04-30","cited_by_count":113},{"id":"1909.07913","title":"Learning to Deceive with Attention-Based Explanations","created":"2019-09-17","cited_by_count":111},{"id":"2103.06503","title":"Fair Mixup: Fairness via Interpolation","created":"2021-03-11","cited_by_count":109},{"id":"2306.07304","title":"A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation","created":"2023-06-11","cited_by_count":109},{"id":"2012.13985","title":"Explaining NLP Models via Minimal Contrastive Editing (MiCE)","created":"2020-12-27","cited_by_count":106},{"id":"1808.02610","title":"L-Shapley and C-Shapley: Efficient Model Interpretation for Structured Data","created":"2018-08-08","cited_by_count":100},{"id":"1909.05088","title":"Getting Gender Right in Neural Machine Translation","created":"2019-09-11","cited_by_count":98},{"id":"2112.04417","title":"What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability Methods","created":"2021-12-06","cited_by_count":98},{"id":"1910.13294","title":"Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control","created":"2019-10-29","cited_by_count":96},{"id":"2106.16163","title":"The MultiBERTs: BERT Reproductions for Robustness Analysis","created":"2021-06-30","cited_by_count":92},{"id":"2005.00652","title":"An Information Bottleneck Approach for Controlling Conciseness in Rationale Extraction","created":"2020-05-01","cited_by_count":69},{"id":"2010.09553","title":"Survey on Causal-based Machine Learning Fairness Notions","created":"2020-10-19","cited_by_count":54},{"id":"2305.15853","title":"Sequential Integrated Gradients: a simple but effective method for explaining language models","created":"2023-05-25","cited_by_count":52},{"id":"2108.13654","title":"Discretized Integrated Gradients for Explaining Language Models","created":"2021-08-31","cited_by_count":46},{"id":"1811.00247","title":"FNNC: Achieving Fairness through Neural Networks","created":"2018-11-01","cited_by_count":43},{"id":"2010.05419","title":"Gradient-based Analysis of NLP Models is Manipulable","created":"2020-10-12","cited_by_count":41},{"id":"2009.05451","title":"A Comparison of LSTM and BERT for Small Corpus","created":"2020-09-11","cited_by_count":40},{"id":"2004.08361","title":"Unsupervised Discovery of Implicit Gender Bias","created":"2020-04-17","cited_by_count":34},{"id":"2203.07893","title":"Gold Doesn't Always Glitter: Spectral Removal of Linear and Nonlinear Guarded Attribute Information","created":"2022-03-15","cited_by_count":34},{"id":"2301.11970","title":"Even if Explanations: Prior Work, Desiderata & Benchmarks for Semi-Factual XAI","created":"2023-01-27","cited_by_count":20},{"id":"1911.04322","title":"Kernel Dependence Regularizers and Gaussian Processes with Applications to Algorithmic Fairness","created":"2019-11-11","cited_by_count":16},{"id":"2205.10200","title":"The Fairness of Credit Scoring Models","created":"2022-05-20","cited_by_count":15},{"id":"1905.11852","title":"EDUCE: Explaining model Decisions through Unsupervised Concepts Extraction","created":"2019-05-28","cited_by_count":13},{"id":"2402.00794","title":"ReAGent: A Model-agnostic Feature Attribution Method for Generative Language Models","created":"2024-02-01","cited_by_count":12},{"id":"2209.09592","title":"Closing the Gender Wage Gap: Adversarial Fairness in Job Recommendation","created":"2022-09-20","cited_by_count":7},{"id":"1912.07579","title":"Algorithms that \"Don't See Color\": Comparing Biases in Lookalike and Special Ad Audiences","created":"2019-12-16","cited_by_count":3}],"next_cursor":null}