{"list":"other","total":247,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"2308.11432","title":"A Survey on Large Language Model based Autonomous Agents","created":"2023-08-22","cited_by_count":2242},{"id":"1910.10045","title":"Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI","created":"2019-10-22","cited_by_count":1552},{"id":"1704.02685","title":"Learning Important Features Through Propagating Activation Differences","created":"2017-04-10","cited_by_count":1458},{"id":"2309.08600","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","created":"2023-09-15","cited_by_count":1420},{"id":"1702.08608","title":"Towards A Rigorous Science of Interpretable Machine Learning","created":"2017-02-28","cited_by_count":1416},{"id":"1706.07269","title":"Explanation in Artificial Intelligence: Insights from the Social Sciences","created":"2017-06-22","cited_by_count":1206},{"id":"2007.04612","title":"Concept Bottleneck Models","created":"2020-07-09","cited_by_count":1032},{"id":"1612.00410","title":"Deep Variational Information Bottleneck","created":"2016-12-01","cited_by_count":930},{"id":"1806.10574","title":"This Looks Like That: Deep Learning for Interpretable Image Recognition","created":"2018-06-27","cited_by_count":737},{"id":"1606.03490","title":"The Mythos of Model Interpretability","created":"2016-06-10","cited_by_count":721},{"id":"2404.19756","title":"KAN: Kolmogorov-Arnold Networks","created":"2024-04-30","cited_by_count":649},{"id":"1908.07442","title":"TabNet: Attentive Interpretable Tabular Learning","created":"2019-08-20","cited_by_count":648},{"id":"1908.04626","title":"Attention is not not Explanation","created":"2019-08-13","cited_by_count":636},{"id":"1707.00600","title":"Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly","created":"2017-07-03","cited_by_count":538},{"id":"1806.07538","title":"Towards Robust Interpretability with Self-Explaining Neural Networks","created":"2018-06-20","cited_by_count":505},{"id":"1812.01193","title":"e-SNLI: Natural Language Inference with Natural Language Explanations","created":"2018-12-04","cited_by_count":468},{"id":"1710.10547","title":"Interpretation of Neural Networks is Fragile","created":"2017-10-29","cited_by_count":444},{"id":"1911.02508","title":"Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods","created":"2019-11-06","cited_by_count":443},{"id":"1906.03731","title":"Is Attention Interpretable?","created":"2019-06-09","cited_by_count":389},{"id":"2012.15445","title":"Explainability in Graph Neural Networks: A Taxonomic Survey","created":"2020-12-31","cited_by_count":384},{"id":"1906.02361","title":"Explain Yourself! Leveraging Language Models for Commonsense Reasoning","created":"2019-06-06","cited_by_count":367},{"id":"2103.11251","title":"Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges","created":"2021-03-20","cited_by_count":367},{"id":"1602.02068","title":"From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification","created":"2016-02-05","cited_by_count":341},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333},{"id":"2004.13912","title":"Neural Additive Models: Interpretable Machine Learning with Neural Nets","created":"2020-04-29","cited_by_count":319},{"id":"2211.11158","title":"Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification","created":"2022-11-21","cited_by_count":312},{"id":"1810.02338","title":"Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding","created":"2018-10-04","cited_by_count":304},{"id":"2205.15480","title":"Post-hoc Concept Bottleneck Models","created":"2022-05-31","cited_by_count":293},{"id":"2012.14261","title":"A Survey on Neural Network Interpretability","created":"2020-12-28","cited_by_count":291},{"id":"2304.06129","title":"Label-Free Concept Bottleneck Models","created":"2023-04-12","cited_by_count":285},{"id":"1606.04155","title":"Rationalizing Neural Predictions","created":"2016-06-13","cited_by_count":281},{"id":"1904.00760","title":"Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet","created":"2019-03-20","cited_by_count":260},{"id":"1802.07814","title":"Learning to Explain: An Information-Theoretic Perspective on Model Interpretation","created":"2018-02-21","cited_by_count":248},{"id":"1910.07969","title":"On Completeness-aware Concept-Based Explanations in Deep Neural Networks","created":"2019-10-17","cited_by_count":239},{"id":"1802.05695","title":"Explainable Prediction of Medical Codes from Clinical Text","created":"2018-02-15","cited_by_count":234},{"id":"2011.07876","title":"A Survey on the Explainability of Supervised Machine Learning","created":"2020-11-16","cited_by_count":227},{"id":"2002.01650","title":"Concept Whitening for Interpretable Image Recognition","created":"2020-02-05","cited_by_count":225},{"id":"2012.02046","title":"Neural Prototype Trees for Interpretable Fine-grained Image Recognition","created":"2020-12-03","cited_by_count":214},{"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":"2204.10532","title":"End-to-end symbolic regression with transformers","created":"2022-04-22","cited_by_count":203},{"id":"2406.11944","title":"Transcoders Find Interpretable LLM Feature Circuits","created":"2024-06-17","cited_by_count":200},{"id":"2106.06427","title":"Neural Symbolic Regression that Scales","created":"2021-06-11","cited_by_count":192},{"id":"2201.12872","title":"Discovering Invariant Rationales for Graph Neural Networks","created":"2022-01-30","cited_by_count":188},{"id":"2201.12987","title":"Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanism","created":"2022-01-31","cited_by_count":171},{"id":"2010.12762","title":"Measuring Association Between Labels and Free-Text Rationales","created":"2020-10-24","cited_by_count":160},{"id":"1806.07259","title":"Learning Equations for Extrapolation and Control","created":"2018-06-19","cited_by_count":156},{"id":"2108.04840","title":"Post-hoc Interpretability for Neural NLP: A Survey","created":"2021-08-10","cited_by_count":156},{"id":"1909.00015","title":"Adaptively Sparse Transformers","created":"2019-08-30","cited_by_count":155},{"id":"2004.14546","title":"WT5?! Training Text-to-Text Models to Explain their Predictions","created":"2020-04-30","cited_by_count":148},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130},{"id":"1905.08160","title":"Interpretable Neural Predictions with Differentiable Binary Variables","created":"2019-05-20","cited_by_count":126},{"id":"2008.05030","title":"Reliable Post hoc Explanations: Modeling Uncertainty in Explainability","created":"2020-08-11","cited_by_count":125},{"id":"2111.06420","title":"Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunities","created":"2021-11-11","cited_by_count":125},{"id":"2010.05563","title":"Graph Information Bottleneck for Subgraph Recognition","created":"2020-10-12","cited_by_count":119},{"id":"2102.07817","title":"What Do We Want From Explainable Artificial Intelligence (XAI)? -- A Stakeholder Perspective on XAI and a Conceptual Model Guiding Interdisciplinary XAI Research","created":"2021-02-15","cited_by_count":119},{"id":"1908.04211","title":"On Identifiability in Transformers","created":"2019-08-12","cited_by_count":116},{"id":"1910.06358","title":"Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability","created":"2019-10-14","cited_by_count":114},{"id":"1909.07913","title":"Learning to Deceive with Attention-Based Explanations","created":"2019-09-17","cited_by_count":111},{"id":"2001.00396","title":"Restricting the Flow: Information Bottlenecks for Attribution","created":"2020-01-02","cited_by_count":110},{"id":"2106.14131","title":"SymbolicGPT: A Generative Transformer Model for Symbolic Regression","created":"2021-06-27","cited_by_count":105},{"id":"2002.06100","title":"Analyzing Differentiable Fuzzy Logic Operators","created":"2020-02-14","cited_by_count":101},{"id":"2306.01574","title":"Probabilistic Concept Bottleneck Models","created":"2023-06-02","cited_by_count":101},{"id":"2401.07927","title":"Are self-explanations from Large Language Models faithful?","created":"2024-01-15","cited_by_count":101},{"id":"1907.09294","title":"The Dangers of Post-hoc Interpretability: Unjustified Counterfactual Explanations","created":"2019-07-22","cited_by_count":97},{"id":"2112.02902","title":"Interpretable Image Classification with Differentiable Prototypes Assignment","created":"2021-12-06","cited_by_count":97},{"id":"2005.12116","title":"NILE : Natural Language Inference with Faithful Natural Language Explanations","created":"2020-05-25","cited_by_count":96},{"id":"2112.00911","title":"ProtGNN: Towards Self-Explaining Graph Neural Networks","created":"2021-12-02","cited_by_count":96},{"id":"1912.04825","title":"Integration of Neural Network-Based Symbolic Regression in Deep Learning for Scientific Discovery","created":"2019-12-10","cited_by_count":93},{"id":"1705.08968","title":"Logic Tensor Networks for Semantic Image Interpretation","created":"2017-05-24","cited_by_count":92},{"id":"1901.09346","title":"Concrete Autoencoders for Differentiable Feature Selection and Reconstruction","created":"2019-01-27","cited_by_count":90},{"id":"1802.00121","title":"Interpreting CNNs via Decision Trees","created":"2018-02-01","cited_by_count":89},{"id":"2011.14340","title":"ProtoPShare: Prototype Sharing for Interpretable Image Classification and Similarity Discovery","created":"2020-11-29","cited_by_count":89},{"id":"2003.09405","title":"Explainable Object-induced Action Decision for Autonomous Vehicles","created":"2020-03-20","cited_by_count":88},{"id":"2106.01613","title":"NODE-GAM: Neural Generalized Additive Model for Interpretable Deep Learning","created":"2021-06-03","cited_by_count":88},{"id":"2205.10268","title":"B-cos Networks: Alignment is All We Need for Interpretability","created":"2022-05-20","cited_by_count":88},{"id":"2210.11584","title":"Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanations","created":"2022-10-20","cited_by_count":85},{"id":"2111.08284","title":"Few-Shot Self-Rationalization with Natural Language Prompts","created":"2021-11-16","cited_by_count":83},{"id":"1906.02500","title":"Towards Interpretable Reinforcement Learning Using Attention Augmented Agents","created":"2019-06-06","cited_by_count":82},{"id":"1907.12207","title":"LassoNet: A Neural Network with Feature Sparsity","created":"2019-07-29","cited_by_count":82},{"id":"2003.07132","title":"GAMI-Net: An Explainable Neural Network based on Generalized Additive Models with Structured Interactions","created":"2020-03-16","cited_by_count":82},{"id":"2006.01067","title":"Aligning Faithful Interpretations with their Social Attribution","created":"2020-06-01","cited_by_count":79},{"id":"2212.07430","title":"Interactive Concept Bottleneck Models","created":"2022-12-14","cited_by_count":79},{"id":"2102.01998","title":"Unbox the Black-box for the Medical Explainable AI via Multi-modal and Multi-centre Data Fusion: A Mini-Review, Two Showcases and Beyond","created":"2021-02-03","cited_by_count":76},{"id":"2102.02201","title":"When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation Data","created":"2021-02-03","cited_by_count":75},{"id":"2108.12055","title":"Towards Self-Explainable Graph Neural Network","created":"2021-08-26","cited_by_count":75},{"id":"2012.00073","title":"TimeSHAP: Explaining Recurrent Models through Sequence Perturbations","created":"2020-11-30","cited_by_count":74},{"id":"2103.10663","title":"XProtoNet: Diagnosis in Chest Radiography with Global and Local Explanations","created":"2021-03-19","cited_by_count":73},{"id":"2205.15612","title":"GlanceNets: Interpretabile, Leak-proof Concept-based Models","created":"2022-05-31","cited_by_count":73},{"id":"1806.06988","title":"Deep Neural Decision Trees","created":"2018-06-19","cited_by_count":72},{"id":"1907.09728","title":"Interpretable and Steerable Sequence Learning via Prototypes","created":"2019-07-23","cited_by_count":72},{"id":"2103.12308","title":"IAIA-BL: A Case-based Interpretable Deep Learning Model for Classification of Mass Lesions in Digital Mammography","created":"2021-03-23","cited_by_count":72},{"id":"1901.10517","title":"Reparameterizable Subset Sampling via Continuous Relaxations","created":"2019-01-29","cited_by_count":70}],"next_cursor":"100"}