{"list":"other","total":60,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"1611.00712","title":"The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables","created":"2016-11-02","cited_by_count":1148},{"id":"1711.00399","title":"Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR","created":"2017-11-01","cited_by_count":1089},{"id":"2103.10360","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","created":"2021-03-18","cited_by_count":1031},{"id":"2210.02414","title":"GLM-130B: An Open Bilingual Pre-trained Model","created":"2022-10-05","cited_by_count":843},{"id":"2012.09838","title":"Transformer Interpretability Beyond Attention Visualization","created":"2020-12-17","cited_by_count":627},{"id":"1905.07697","title":"Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations","created":"2019-05-19","cited_by_count":614},{"id":"1809.06514","title":"Actionable Recourse in Linear Classification","created":"2018-09-18","cited_by_count":328},{"id":"2103.15679","title":"Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers","created":"2021-03-29","cited_by_count":320},{"id":"1906.01629","title":"Exact Combinatorial Optimization with Graph Convolutional Neural Networks","created":"2019-06-04","cited_by_count":318},{"id":"2006.04315","title":"Counterfactual VQA: A Cause-Effect Look at Language Bias","created":"2020-06-08","cited_by_count":266},{"id":"1802.07623","title":"Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives","created":"2018-02-21","cited_by_count":262},{"id":"2002.09291","title":"Transformer Hawkes Process","created":"2020-02-21","cited_by_count":235},{"id":"1810.00337","title":"Learning to Perform Local Rewriting for Combinatorial Optimization","created":"2018-09-30","cited_by_count":185},{"id":"2010.10596","title":"Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Review","created":"2020-10-20","cited_by_count":174},{"id":"1909.12127","title":"Intensity-Free Learning of Temporal Point Processes","created":"2019-09-26","cited_by_count":140},{"id":"1907.09615","title":"Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systems","created":"2019-07-22","cited_by_count":131},{"id":"2111.09259","title":"Acquisition of Chess Knowledge in AlphaZero","created":"2021-11-17","cited_by_count":123},{"id":"1905.09690","title":"Fully Neural Network based Model for General Temporal Point Processes","created":"2019-05-23","cited_by_count":122},{"id":"1511.06038","title":"Neural Variational Inference for Text Processing","created":"2015-11-19","cited_by_count":111},{"id":"1906.04859","title":"Reinforcement Learning for Integer Programming: Learning to Cut","created":"2019-06-11","cited_by_count":111},{"id":"2201.00044","title":"Transformer Embeddings of Irregularly Spaced Events and Their Participants","created":"2021-12-31","cited_by_count":93},{"id":"1506.02594","title":"SEISMIC: A Self-Exciting Point Process Model for Predicting Tweet Popularity","created":"2015-06-08","cited_by_count":76},{"id":"1602.04511","title":"Learning Granger Causality for Hawkes Processes","created":"2016-02-14","cited_by_count":69},{"id":"1912.05743","title":"Exploratory Not Explanatory: Counterfactual Analysis of Saliency Maps for Deep Reinforcement Learning","created":"2019-12-09","cited_by_count":60},{"id":"2108.10539","title":"Counterfactual Explainable Recommendation","created":"2021-08-24","cited_by_count":60},{"id":"2206.08311","title":"Continuous-Time Modeling of Counterfactual Outcomes Using Neural Controlled Differential Equations","created":"2022-06-16","cited_by_count":59},{"id":"2210.01753","title":"HYPRO: A Hybridly Normalized Probabilistic Model for Long-Horizon Prediction of Event Sequences","created":"2022-10-04","cited_by_count":57},{"id":"2203.16586","title":"Counterfactual Cycle-Consistent Learning for Instruction Following and Generation in Vision-Language Navigation","created":"2022-03-30","cited_by_count":51},{"id":"2101.07600","title":"Interpretable Models for Granger Causality Using Self-explaining Neural Networks","created":"2021-01-19","cited_by_count":45},{"id":"2203.02878","title":"A Survey for Solving Mixed Integer Programming via Machine Learning","created":"2022-03-06","cited_by_count":44},{"id":"1906.00117","title":"Model Agnostic Contrastive Explanations for Structured Data","created":"2019-05-31","cited_by_count":41},{"id":"2106.00285","title":"Shapley Counterfactual Credits for Multi-Agent Reinforcement Learning","created":"2021-06-01","cited_by_count":38},{"id":"2107.02776","title":"Counterfactual Explanations in Sequential Decision Making Under Uncertainty","created":"2021-07-06","cited_by_count":37},{"id":"2002.07906","title":"CAUSE: Learning Granger Causality from Event Sequences using Attribution Methods","created":"2020-02-18","cited_by_count":36},{"id":"2106.06631","title":"Optimal Counterfactual Explanations in Tree Ensembles","created":"2021-06-11","cited_by_count":36},{"id":"1911.08378","title":"PRINCE: Provider-side Interpretability with Counterfactual Explanations in Recommender Systems","created":"2019-11-19","cited_by_count":35},{"id":"2009.02623","title":"Information Theoretic Counterfactual Learning from Missing-Not-At-Random Feedback","created":"2020-09-06","cited_by_count":30},{"id":"1806.05626","title":"NCRF++: An Open-source Neural Sequence Labeling Toolkit","created":"2018-06-14","cited_by_count":29},{"id":"2105.05008","title":"Counterfactual Explanations for Neural Recommenders","created":"2021-05-11","cited_by_count":27},{"id":"2002.05522","title":"BRPO: Batch Residual Policy Optimization","created":"2020-02-08","cited_by_count":25},{"id":"2110.11960","title":"ReLAX: Reinforcement Learning Agent eXplainer for Arbitrary Predictive Models","created":"2021-10-22","cited_by_count":25},{"id":"2302.12465","title":"PaGE-Link: Path-based Graph Neural Network Explanation for Heterogeneous Link Prediction","created":"2023-02-24","cited_by_count":25},{"id":"1703.07823","title":"Fake News Mitigation via Point Process Based Intervention","created":"2017-03-22","cited_by_count":24},{"id":"1910.00057","title":"Synthesizing Action Sequences for Modifying Model Decisions","created":"2019-09-30","cited_by_count":22},{"id":"2204.13844","title":"User-controllable Recommendation Against Filter Bubbles","created":"2022-04-29","cited_by_count":22},{"id":"2109.02444","title":"Top-N Recommendation with Counterfactual User Preference Simulation","created":"2021-09-02","cited_by_count":21},{"id":"2111.07603","title":"Counterfactual Temporal Point Processes","created":"2021-11-15","cited_by_count":20},{"id":"2210.07518","title":"Counterfactual Neural Temporal Point Process for Estimating Causal Influence of Misinformation on Social Media","created":"2022-10-14","cited_by_count":20},{"id":"2110.15454","title":"VigDet: Knowledge Informed Neural Temporal Point Process for Coordination Detection on Social Media","created":"2021-10-28","cited_by_count":14},{"id":"2208.10671","title":"Cardinality-Regularized Hawkes-Granger Model","created":"2022-08-23","cited_by_count":14},{"id":"2206.06124","title":"Causal Discovery in Hawkes Processes by Minimum Description Length","created":"2022-06-10","cited_by_count":11},{"id":"2009.00481","title":"Efficient Message Passing for 0-1 ILPs with Binary Decision Diagrams","created":"2020-09-01","cited_by_count":8},{"id":"1908.04573","title":"Competitive Multi-Agent Deep Reinforcement Learning with Counterfactual Thinking","created":"2019-08-13","cited_by_count":5},{"id":"2307.00165","title":"Counterfactual Collaborative Reasoning","created":"2023-06-30","cited_by_count":3},{"id":"2202.07356","title":"Realistic Counterfactual Explanations with Learned Relations","created":"2022-02-15","cited_by_count":2}],"next_cursor":null}