{"list":"other","total":64,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"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":"1905.00414","title":"Similarity of Neural Network Representations Revisited","created":"2019-05-01","cited_by_count":1755},{"id":"2210.03350","title":"Measuring and Narrowing the Compositionality Gap in Language Models","created":"2022-10-07","cited_by_count":1075},{"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":"1906.04341","title":"What Does BERT Look At? An Analysis of BERT's Attention","created":"2019-06-11","cited_by_count":1003},{"id":"1706.05394","title":"A Closer Look at Memorization in Deep Networks","created":"2017-06-16","cited_by_count":942},{"id":"1902.10186","title":"Attention is not Explanation","created":"2019-02-26","cited_by_count":929},{"id":"1905.09418","title":"Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned","created":"2019-05-23","cited_by_count":856},{"id":"2301.05217","title":"Progress measures for grokking via mechanistic interpretability","created":"2023-01-12","cited_by_count":839},{"id":"2005.00928","title":"Quantifying Attention Flow in Transformers","created":"2020-05-02","cited_by_count":775},{"id":"2201.02177","title":"Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets","created":"2022-01-06","cited_by_count":629},{"id":"1912.00582","title":"BLiMP: The Benchmark of Linguistic Minimal Pairs for English","created":"2019-12-02","cited_by_count":564},{"id":"2109.02846","title":"Datasets: A Community Library for Natural Language Processing","created":"2021-09-07","cited_by_count":530},{"id":"2304.15004","title":"Are Emergent Abilities of Large Language Models a Mirage?","created":"2023-04-28","cited_by_count":523},{"id":"1703.00810","title":"Opening the Black Box of Deep Neural Networks via Information","created":"2017-03-02","cited_by_count":503},{"id":"1906.03731","title":"Is Attention Interpretable?","created":"2019-06-09","cited_by_count":389},{"id":"2006.07710","title":"The Pitfalls of Simplicity Bias in Neural Networks","created":"2020-06-13","cited_by_count":351},{"id":"1806.05759","title":"Insights on representational similarity in neural networks with canonical correlation","created":"2018-06-14","cited_by_count":324},{"id":"1905.12784","title":"Intrinsic dimension of data representations in deep neural networks","created":"2019-05-29","cited_by_count":282},{"id":"2011.09468","title":"Gradient Starvation: A Learning Proclivity in Neural Networks","created":"2020-11-18","cited_by_count":267},{"id":"1803.06992","title":"Estimating the intrinsic dimension of datasets by a minimal neighborhood information","created":"2018-03-19","cited_by_count":250},{"id":"2205.10343","title":"Towards Understanding Grokking: An Effective Theory of Representation Learning","created":"2022-05-20","cited_by_count":230},{"id":"2003.02218","title":"The large learning rate phase of deep learning: the catapult mechanism","created":"2020-03-04","cited_by_count":216},{"id":"1905.11604","title":"SGD on Neural Networks Learns Functions of Increasing Complexity","created":"2019-05-28","cited_by_count":204},{"id":"2004.12265","title":"Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias","created":"2020-04-26","cited_by_count":191},{"id":"2207.08799","title":"Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit","created":"2022-07-18","cited_by_count":187},{"id":"1805.08522","title":"Deep learning generalizes because the parameter-function map is biased towards simple functions","created":"2018-05-22","cited_by_count":183},{"id":"2002.09572","title":"The Break-Even Point on Optimization Trajectories of Deep Neural Networks","created":"2020-02-21","cited_by_count":150},{"id":"2210.01117","title":"Omnigrok: Grokking Beyond Algorithmic Data","created":"2022-10-03","cited_by_count":146},{"id":"2006.12433","title":"What shapes feature representations? Exploring datasets, architectures, and training","created":"2020-06-22","cited_by_count":126},{"id":"2111.09259","title":"Acquisition of Chess Knowledge in AlphaZero","created":"2021-11-17","cited_by_count":123},{"id":"2210.14891","title":"Broken Neural Scaling Laws","created":"2022-10-26","cited_by_count":109},{"id":"2012.03107","title":"When Do Curricula Work?","created":"2020-12-05","cited_by_count":106},{"id":"2206.04817","title":"The Slingshot Mechanism: An Empirical Study of Adaptive Optimizers and the Grokking Phenomenon","created":"2022-06-10","cited_by_count":94},{"id":"2305.18887","title":"How Does Information Bottleneck Help Deep Learning?","created":"2023-05-30","cited_by_count":93},{"id":"2106.16163","title":"The MultiBERTs: BERT Reproductions for Robustness Analysis","created":"2021-06-30","cited_by_count":92},{"id":"2303.11873","title":"A Tale of Two Circuits: Grokking as Competition of Sparse and Dense Subnetworks","created":"2023-03-21","cited_by_count":83},{"id":"2212.09803","title":"Training Trajectories of Language Models Across Scales","created":"2022-12-19","cited_by_count":81},{"id":"2104.07885","title":"Probing Across Time: What Does RoBERTa Know and When?","created":"2021-04-16","cited_by_count":73},{"id":"2108.05885","title":"The paradox of the compositionality of natural language: a neural machine translation case study","created":"2021-08-12","cited_by_count":59},{"id":"2010.02180","title":"Pareto Probing: Trading Off Accuracy for Complexity","created":"2020-10-05","cited_by_count":55},{"id":"2305.18741","title":"Grokking of Hierarchical Structure in Vanilla Transformers","created":"2023-05-30","cited_by_count":53},{"id":"2211.01288","title":"Characterizing Intrinsic Compositionality in Transformers with Tree Projections","created":"2022-11-02","cited_by_count":41},{"id":"2105.14002","title":"What if This Modified That? Syntactic Interventions via Counterfactual Embeddings","created":"2021-05-28","cited_by_count":39},{"id":"2109.06096","title":"The Grammar-Learning Trajectories of Neural Language Models","created":"2021-09-13","cited_by_count":36},{"id":"2305.15614","title":"Reverse Engineering Self-Supervised Learning","created":"2023-05-24","cited_by_count":33},{"id":"2010.02480","title":"Pretrained Language Model Embryology: The Birth of ALBERT","created":"2020-10-06","cited_by_count":30},{"id":"2105.14652","title":"Attention Flows are Shapley Value Explanations","created":"2021-05-31","cited_by_count":30},{"id":"2205.15301","title":"Can Transformer be Too Compositional? Analysing Idiom Processing in Neural Machine Translation","created":"2022-05-30","cited_by_count":28},{"id":"2202.06749","title":"Information Flow in Deep Neural Networks","created":"2022-02-10","cited_by_count":22},{"id":"2304.01910","title":"On the Variance of Neural Network Training with respect to Test Sets and Distributions","created":"2023-04-04","cited_by_count":22},{"id":"2308.09543","title":"Latent State Models of Training Dynamics","created":"2023-08-18","cited_by_count":16},{"id":"1904.10922","title":"The Scientific Method in the Science of Machine Learning","created":"2019-04-24","cited_by_count":15},{"id":"2003.01262","title":"Selectivity considered harmful: evaluating the causal impact of class selectivity in DNNs","created":"2020-03-03","cited_by_count":15},{"id":"2010.04650","title":"LSTMs Compose (and Learn) Bottom-Up","created":"2020-10-06","cited_by_count":11},{"id":"2211.14673","title":"Evaluation Beyond Task Performance: Analyzing Concepts in AlphaZero in Hex","created":"2022-11-26","cited_by_count":8},{"id":"2305.17409","title":"On the special role of class-selective neurons in early training","created":"2023-05-27","cited_by_count":5}],"next_cursor":null}