{"list":"other","total":88,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"1704.01212","title":"Neural Message Passing for Quantum Chemistry","created":"2017-04-04","cited_by_count":3487},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1903.02428","title":"Fast Graph Representation Learning with PyTorch Geometric","created":"2019-03-06","cited_by_count":2434},{"id":"1312.6034","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","created":"2013-12-20","cited_by_count":2371},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1610.02413","title":"Equality of Opportunity in Supervised Learning","created":"2016-10-07","cited_by_count":2007},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"1908.09635","title":"A Survey on Bias and Fairness in Machine Learning","created":"2019-08-23","cited_by_count":1917},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"1704.02685","title":"Learning Important Features Through Propagating Activation Differences","created":"2017-04-10","cited_by_count":1458},{"id":"1702.08608","title":"Towards A Rigorous Science of Interpretable Machine Learning","created":"2017-02-28","cited_by_count":1416},{"id":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1296},{"id":"1802.00420","title":"Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples","created":"2018-02-01","cited_by_count":1268},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"id":"1706.03825","title":"SmoothGrad: removing noise by adding noise","created":"2017-06-12","cited_by_count":1109},{"id":"2108.12409","title":"Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation","created":"2021-08-27","cited_by_count":1103},{"id":"2007.04612","title":"Concept Bottleneck Models","created":"2020-07-09","cited_by_count":1032},{"id":"1906.04341","title":"What Does BERT Look At? An Analysis of BERT's Attention","created":"2019-06-11","cited_by_count":1003},{"id":"1902.10186","title":"Attention is not Explanation","created":"2019-02-26","cited_by_count":929},{"id":"1805.12152","title":"Robustness May Be at Odds with Accuracy","created":"2018-05-30","cited_by_count":880},{"id":"1703.06856","title":"Counterfactual Fairness","created":"2017-03-20","cited_by_count":804},{"id":"1909.05858","title":"CTRL: A Conditional Transformer Language Model for Controllable Generation","created":"2019-09-11","cited_by_count":762},{"id":"1806.10574","title":"This Looks Like That: Deep Learning for Interpretable Image Recognition","created":"2018-06-27","cited_by_count":737},{"id":"1903.03894","title":"GNNExplainer: Generating Explanations for Graph Neural Networks","created":"2019-03-10","cited_by_count":737},{"id":"1606.03490","title":"The Mythos of Model Interpretability","created":"2016-06-10","cited_by_count":721},{"id":"2106.13884","title":"Multimodal Few-Shot Learning with Frozen Language Models","created":"2021-06-25","cited_by_count":661},{"id":"2102.07350","title":"Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm","created":"2021-02-15","cited_by_count":606},{"id":"1905.12616","title":"Defending Against Neural Fake News","created":"2019-05-29","cited_by_count":559},{"id":"2009.07896","title":"Captum: A unified and generic model interpretability library for PyTorch","created":"2020-09-16","cited_by_count":547},{"id":"1806.10758","title":"A Benchmark for Interpretability Methods in Deep Neural Networks","created":"2018-06-28","cited_by_count":476},{"id":"1909.12434","title":"Learning the Difference that Makes a Difference with Counterfactually-Augmented Data","created":"2019-09-26","cited_by_count":439},{"id":"2012.15445","title":"Explainability in Graph Neural Networks: A Taxonomic Survey","created":"2020-12-31","cited_by_count":384},{"id":"1506.06579","title":"Understanding Neural Networks Through Deep Visualization","created":"2015-06-22","cited_by_count":334},{"id":"1711.00867","title":"The (Un)reliability of saliency methods","created":"2017-11-02","cited_by_count":333},{"id":"1810.01943","title":"AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias","created":"2018-10-03","cited_by_count":319},{"id":"2003.07892","title":"Calibration of Pre-trained Transformers","created":"2020-03-17","cited_by_count":315},{"id":"1806.08049","title":"On the Robustness of Interpretability Methods","created":"2018-06-21","cited_by_count":314},{"id":"1904.07451","title":"Counterfactual Visual Explanations","created":"2019-04-16","cited_by_count":313},{"id":"1906.05714","title":"A Multiscale Visualization of Attention in the Transformer Model","created":"2019-06-12","cited_by_count":292},{"id":"2011.09468","title":"Gradient Starvation: A Learning Proclivity in Neural Networks","created":"2020-11-18","cited_by_count":267},{"id":"2002.06278","title":"Algorithmic Recourse: from Counterfactual Explanations to Interventions","created":"2020-02-14","cited_by_count":250},{"id":"1506.00019","title":"A Critical Review of Recurrent Neural Networks for Sequence Learning","created":"2015-05-29","cited_by_count":224},{"id":"1907.02584","title":"Interpretable Counterfactual Explanations Guided by Prototypes","created":"2019-07-03","cited_by_count":223},{"id":"1708.08296","title":"Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models","created":"2017-08-28","cited_by_count":206},{"id":"2010.00711","title":"A Survey of the State of Explainable AI for Natural Language Processing","created":"2020-10-01","cited_by_count":206},{"id":"2002.11097","title":"Problems with Shapley-value-based explanations as feature importance measures","created":"2020-02-25","cited_by_count":200},{"id":"1706.02744","title":"Avoiding Discrimination through Causal Reasoning","created":"2017-06-08","cited_by_count":194},{"id":"2005.00631","title":"Evaluating and Aggregating Feature-based Model Explanations","created":"2020-05-01","cited_by_count":188},{"id":"1909.03012","title":"One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques","created":"2019-09-06","cited_by_count":164},{"id":"1905.13686","title":"Explainability Techniques for Graph Convolutional Networks","created":"2019-05-31","cited_by_count":161},{"id":"1506.02078","title":"Visualizing and Understanding Recurrent Networks","created":"2015-06-05","cited_by_count":160},{"id":"1712.09923","title":"What do we need to build explainable AI systems for the medical domain?","created":"2017-12-28","cited_by_count":129},{"id":"2010.04050","title":"A survey of algorithmic recourse: definitions, formulations, solutions, and prospects","created":"2020-10-08","cited_by_count":118},{"id":"1711.10604","title":"TensorFlow Distributions","created":"2017-11-28","cited_by_count":106},{"id":"1807.02910","title":"Model Agnostic Supervised Local Explanations","created":"2018-07-09","cited_by_count":83},{"id":"2106.00545","title":"Counterfactual Invariance to Spurious Correlations: Why and How to Pass Stress Tests","created":"2021-05-31","cited_by_count":77},{"id":"1909.09251","title":"AllenNLP Interpret: A Framework for Explaining Predictions of NLP Models","created":"2019-09-19","cited_by_count":74},{"id":"2206.09677","title":"GraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networks","created":"2022-06-20","cited_by_count":58},{"id":"2409.02387","title":"Large Language Models and Cognitive Science: A Comprehensive Review of Similarities, Differences, and Challenges","created":"2024-09-04","cited_by_count":49},{"id":"1307.6769","title":"Streaming Variational Bayes","created":"2013-07-25","cited_by_count":48},{"id":"1606.09066","title":"Making Tree Ensembles Interpretable: A Bayesian Model Selection Approach","created":"2016-06-29","cited_by_count":27},{"id":"2409.08087","title":"Securing Large Language Models: Addressing Bias, Misinformation, and Prompt Attacks","created":"2024-09-12","cited_by_count":26},{"id":"1902.08336","title":"On the Sensitivity of Adversarial Robustness to Input Data Distributions","created":"2019-02-22","cited_by_count":20},{"id":"1507.05259","title":"Fairness Constraints: Mechanisms for Fair Classification","created":"2015-07-19","cited_by_count":10},{"id":"1606.03976","title":"Estimating individual treatment effect: generalization bounds and algorithms","created":"2016-06-13","cited_by_count":4},{"id":"2106.10112","title":"Deep Reinforcement Learning Models Predict Visual Responses in the Brain: A Preliminary Result","created":"2021-06-18","cited_by_count":2},{"id":"1906.11197","title":"Java Generics: An Order-Theoretic Approach (Abridged Outline)","created":"2019-06-20","cited_by_count":1},{"id":"2004.05587","title":"Who are Political Retweeters?, Demographic comparison of political retweeters with retweeters of non-political personalities","created":"2020-04-12","cited_by_count":1},{"id":"2011.06304","title":"Machine Learning Interpretability Meets TLS Fingerprinting","created":"2020-11-12","cited_by_count":1},{"id":"2011.12558","title":"Signal Sets on Time Scales with Application to Hybrid Systems","created":"2020-11-25","cited_by_count":1}],"next_cursor":null}