{"list":"other","total":82,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"1703.04730","title":"Understanding Black-box Predictions via Influence Functions","created":"2017-03-14","cited_by_count":1741},{"id":"1612.08242","title":"YOLO9000: Better, Faster, Stronger","created":"2016-12-25","cited_by_count":1431},{"id":"1702.08608","title":"Towards A Rigorous Science of Interpretable Machine Learning","created":"2017-02-28","cited_by_count":1416},{"id":"1803.09010","title":"Datasheets for Datasets","created":"2018-03-23","cited_by_count":1386},{"id":"1711.11279","title":"Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)","created":"2017-11-30","cited_by_count":1319},{"id":"1607.06520","title":"Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings","created":"2016-07-21","cited_by_count":1312},{"id":"2211.00593","title":"Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small","created":"2022-11-01","cited_by_count":1165},{"id":"1706.03825","title":"SmoothGrad: removing noise by adding noise","created":"2017-06-12","cited_by_count":1109},{"id":"1910.09457","title":"Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods","created":"2019-10-21","cited_by_count":913},{"id":"1806.07421","title":"RISE: Randomized Input Sampling for Explanation of Black-box Models","created":"2018-06-19","cited_by_count":838},{"id":"2011.06225","title":"A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges","created":"2020-11-12","cited_by_count":819},{"id":"1910.10699","title":"Contrastive Representation Distillation","created":"2019-10-23","cited_by_count":748},{"id":"1704.05796","title":"Network Dissection: Quantifying Interpretability of Deep Visual Representations","created":"2017-04-19","cited_by_count":708},{"id":"2002.00388","title":"A Survey on Knowledge Graphs: Representation, Acquisition and Applications","created":"2020-02-02","cited_by_count":643},{"id":"2003.02320","title":"Knowledge Graphs","created":"2020-03-04","cited_by_count":621},{"id":"1905.07697","title":"Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations","created":"2019-05-19","cited_by_count":614},{"id":"2210.13382","title":"Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task","created":"2022-10-24","cited_by_count":431},{"id":"2103.14749","title":"Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarks","created":"2021-03-26","cited_by_count":395},{"id":"2004.10645","title":"AmbigQA: Answering Ambiguous Open-domain Questions","created":"2020-04-22","cited_by_count":390},{"id":"2305.13534","title":"How Language Model Hallucinations Can Snowball","created":"2023-05-22","cited_by_count":311},{"id":"1909.10155","title":"Verified Uncertainty Calibration","created":"2019-09-23","cited_by_count":309},{"id":"2012.05345","title":"Data and its (dis)contents: A survey of dataset development and use in machine learning research","created":"2020-12-09","cited_by_count":260},{"id":"2006.16923","title":"Large image datasets: A pyrrhic win for computer vision?","created":"2020-06-24","cited_by_count":237},{"id":"1802.05695","title":"Explainable Prediction of Medical Codes from Clinical Text","created":"2018-02-15","cited_by_count":234},{"id":"1907.04135","title":"The What-If Tool: Interactive Probing of Machine Learning Models","created":"2019-07-09","cited_by_count":207},{"id":"1901.10002","title":"A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle","created":"2019-01-28","cited_by_count":193},{"id":"2005.04611","title":"How Context Affects Language Models' Factual Predictions","created":"2020-05-10","cited_by_count":181},{"id":"2106.00737","title":"Implicit Representations of Meaning in Neural Language Models","created":"2021-06-01","cited_by_count":180},{"id":"2105.13093","title":"Towards Understanding Knowledge Distillation","created":"2021-05-27","cited_by_count":158},{"id":"2204.10965","title":"CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks","created":"2022-04-23","cited_by_count":147},{"id":"2304.00740","title":"Inspecting and Editing Knowledge Representations in Language Models","created":"2023-04-03","cited_by_count":141},{"id":"2209.07572","title":"Power to the People? Opportunities and Challenges for Participatory AI","created":"2022-09-15","cited_by_count":138},{"id":"2201.11114","title":"Natural Language Descriptions of Deep Visual Features","created":"2022-01-26","cited_by_count":137},{"id":"2401.06775","title":"Large language models in healthcare and medical domain: A review","created":"2023-12-12","cited_by_count":127},{"id":"1906.02825","title":"XRAI: Better Attributions Through Regions","created":"2019-06-06","cited_by_count":116},{"id":"2310.08744","title":"Circuit Component Reuse Across Tasks in Transformer Language Models","created":"2023-10-12","cited_by_count":108},{"id":"2006.16736","title":"Beyond accuracy: quantifying trial-by-trial behaviour of CNNs and humans by measuring error consistency","created":"2020-06-30","cited_by_count":78},{"id":"2211.01201","title":"Human alignment of neural network representations","created":"2022-11-02","cited_by_count":74},{"id":"1804.09299","title":"Seq2Seq-Vis: A Visual Debugging Tool for Sequence-to-Sequence Models","created":"2018-04-25","cited_by_count":69},{"id":"2101.09824","title":"Beyond Expertise and Roles: A Framework to Characterize the Stakeholders of Interpretable Machine Learning and their Needs","created":"2021-01-24","cited_by_count":64},{"id":"2304.10909","title":"Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study","created":"2023-04-21","cited_by_count":49},{"id":"2310.16410","title":"Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZero","created":"2023-10-25","cited_by_count":42},{"id":"1912.04853","title":"Embedding Comparator: Visualizing Differences in Global Structure and Local Neighborhoods via Small Multiples","created":"2019-12-10","cited_by_count":38},{"id":"2203.11092","title":"Automated Clinical Coding: What, Why, and Where We Are?","created":"2022-03-21","cited_by_count":33},{"id":"2302.04732","title":"Zeno: An Interactive Framework for Behavioral Evaluation of Machine Learning","created":"2023-02-09","cited_by_count":33},{"id":"2210.03709","title":"Understanding Practices, Challenges, and Opportunities for User-Engaged Algorithm Auditing in Industry Practice","created":"2022-10-07","cited_by_count":32},{"id":"1810.03805","title":"What made you do this? Understanding black-box decisions with sufficient input subsets","created":"2018-10-09","cited_by_count":31},{"id":"2107.09234","title":"Shared Interest: Measuring Human-AI Alignment to Identify Recurring Patterns in Model Behavior","created":"2021-07-20","cited_by_count":29},{"id":"2003.08907","title":"Overinterpretation reveals image classification model pathologies","created":"2020-03-19","cited_by_count":28},{"id":"2201.11569","title":"Human Interpretation of Saliency-based Explanation Over Text","created":"2022-01-27","cited_by_count":25},{"id":"2206.03390","title":"Gender Bias in Word Embeddings: A Comprehensive Analysis of Frequency, Syntax, and Semantics","created":"2022-06-07","cited_by_count":24},{"id":"2109.05289","title":"What's in a Name? Answer Equivalence For Open-Domain Question Answering","created":"2021-09-11","cited_by_count":21},{"id":"2202.08946","title":"Symphony: Composing Interactive Interfaces for Machine Learning","created":"2022-02-18","cited_by_count":18},{"id":"2401.04695","title":"Narrowing the Knowledge Evaluation Gap: Open-Domain Question Answering with Multi-Granularity Answers","created":"2024-01-09","cited_by_count":18},{"id":"2202.02641","title":"Emblaze: Illuminating Machine Learning Representations through Interactive Comparison of Embedding Spaces","created":"2022-02-05","cited_by_count":16},{"id":"2402.00491","title":"EXMOS: Explanatory Model Steering Through Multifaceted Explanations and Data Configurations","created":"2024-02-01","cited_by_count":14},{"id":"2304.05967","title":"Angler: Helping Machine Translation Practitioners Prioritize Model Improvements","created":"2023-04-12","cited_by_count":12},{"id":"1902.03129","title":"Towards Automatic Concept-based Explanations","created":"2019-02-07","cited_by_count":11},{"id":"2206.02958","title":"Saliency Cards: A Framework to Characterize and Compare Saliency Methods","created":"2022-06-07","cited_by_count":11},{"id":"2307.16526","title":"No Fair Lunch: A Causal Perspective on Dataset Bias in Machine Learning for Medical Imaging","created":"2023-07-31","cited_by_count":11},{"id":"2107.07013","title":"Passive Attention in Artificial Neural Networks Predicts Human Visual Selectivity","created":"2021-07-14","cited_by_count":10},{"id":"2401.08672","title":"Concept Alignment","created":"2024-01-09","cited_by_count":10},{"id":"1704.00260","title":"Aligned Image-Word Representations Improve Inductive Transfer Across Vision-Language Tasks","created":"2017-04-02","cited_by_count":9},{"id":"2208.03284","title":"Interpretable Uncertainty Quantification in AI for HEP","created":"2022-08-05","cited_by_count":8},{"id":"2210.05159","title":"Can Language Models Be Specific? How?","created":"2022-10-11","cited_by_count":8},{"id":"2403.06431","title":"From Fitting Participation to Forging Relationships: The Art of Participatory ML","created":"2024-03-11","cited_by_count":8},{"id":"2404.03085","title":"Talaria: Interactively Optimizing Machine Learning Models for Efficient Inference","created":"2024-04-03","cited_by_count":6},{"id":"2405.01286","title":"Data Feminism for AI","created":"2024-05-02","cited_by_count":6},{"id":"2106.13093","title":"Human-in-the-loop model explanation via verbatim boundary identification in generated neighborhoods","created":"2021-06-24","cited_by_count":4},{"id":"2108.04742","title":"The information of attribute uncertainties: what convolutional neural networks can learn about errors in input data","created":"2021-08-10","cited_by_count":4},{"id":"2310.02063","title":"Lessons Learned from EXMOS User Studies: A Technical Report Summarizing Key Takeaways from User Studies Conducted to Evaluate The EXMOS Platform","created":"2023-10-03","cited_by_count":4}],"next_cursor":null}