{"list":"other","total":64,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"1810.03993","title":"Model Cards for Model Reporting","created":"2018-10-05","cited_by_count":1080},{"id":"2010.12421","title":"TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classification","created":"2020-10-23","cited_by_count":417},{"id":"2006.14779","title":"Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance","created":"2020-06-26","cited_by_count":399},{"id":"2001.02114","title":"Effect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision Making","created":"2020-01-07","cited_by_count":281},{"id":"2006.01862","title":"Consistent Estimators for Learning to Defer to an Expert","created":"2020-06-02","cited_by_count":271},{"id":"1711.06664","title":"Predict Responsibly: Improving Fairness and Accuracy by Learning to Defer","created":"2017-11-17","cited_by_count":233},{"id":"2211.03540","title":"Measuring Progress on Scalable Oversight for Large Language Models","created":"2022-11-04","cited_by_count":225},{"id":"2005.01831","title":"Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?","created":"2020-05-04","cited_by_count":190},{"id":"1811.07901","title":"On Human Predictions with Explanations and Predictions of Machine Learning Models: A Case Study on Deception Detection","created":"2018-11-19","cited_by_count":159},{"id":"2203.14960","title":"Domino: Discovering Systematic Errors with Cross-Modal Embeddings","created":"2022-03-24","cited_by_count":156},{"id":"2206.15331","title":"GitHub Copilot AI pair programmer: Asset or Liability?","created":"2022-06-30","cited_by_count":152},{"id":"1612.01079","title":"End-to-end Learning of Driving Models from Large-scale Video Datasets","created":"2016-12-04","cited_by_count":148},{"id":"2001.08298","title":"Proxy Tasks and Subjective Measures Can Be Misleading in Evaluating Explainable AI Systems","created":"2020-01-22","cited_by_count":139},{"id":"2212.06823","title":"Explanations Can Reduce Overreliance on AI Systems During Decision-Making","created":"2022-12-13","cited_by_count":111},{"id":"1903.12220","title":"The Algorithmic Automation Problem: Prediction, Triage, and Human Effort","created":"2019-03-28","cited_by_count":101},{"id":"2001.05871","title":"\"Why is 'Chicago' deceptive?\" Towards Building Model-Driven Tutorials for Humans","created":"2020-01-14","cited_by_count":86},{"id":"2112.11471","title":"Towards a Science of Human-AI Decision Making: A Survey of Empirical Studies","created":"2021-12-21","cited_by_count":86},{"id":"2206.14754","title":"Distilling Model Failures as Directions in Latent Space","created":"2022-06-29","cited_by_count":82},{"id":"1902.00006","title":"An Evaluation of the Human-Interpretability of Explanation","created":"2019-01-31","cited_by_count":71},{"id":"2301.06197","title":"Who Should Predict? Exact Algorithms For Learning to Defer to Humans","created":"2023-01-15","cited_by_count":70},{"id":"2204.11788","title":"Human-AI Collaboration via Conditional Delegation: A Case Study of Content Moderation","created":"2022-04-25","cited_by_count":67},{"id":"2301.05809","title":"Who Should I Trust: AI or Myself? Leveraging Human and AI Correctness Likelihood to Promote Appropriate Trust in AI-Assisted Decision-Making","created":"2023-01-14","cited_by_count":67},{"id":"2012.15349","title":"DynaSent: A Dynamic Benchmark for Sentiment Analysis","created":"2020-12-30","cited_by_count":63},{"id":"2107.00758","title":"The Spotlight: A General Method for Discovering Systematic Errors in Deep Learning Models","created":"2021-07-01","cited_by_count":63},{"id":"2205.04596","title":"When does dough become a bagel? Analyzing the remaining mistakes on ImageNet","created":"2022-05-09","cited_by_count":61},{"id":"2101.05303","title":"Understanding the Effect of Out-of-distribution Examples and Interactive Explanations on Human-AI Decision Making","created":"2021-01-13","cited_by_count":58},{"id":"2201.12323","title":"Describing Differences between Text Distributions with Natural Language","created":"2022-01-28","cited_by_count":54},{"id":"1810.09648","title":"What can AI do for me: Evaluating Machine Learning Interpretations in Cooperative Play","created":"2018-10-23","cited_by_count":53},{"id":"1810.12366","title":"Do Explanations make VQA Models more Predictable to a Human?","created":"2018-10-29","cited_by_count":52},{"id":"2305.07722","title":"In Search of Verifiability: Explanations Rarely Enable Complementary Performance in AI-Advised Decision Making","created":"2023-05-12","cited_by_count":50},{"id":"2207.09584","title":"Sample Efficient Learning of Predictors that Complement Humans","created":"2022-07-19","cited_by_count":46},{"id":"2208.08831","title":"Discovering Bugs in Vision Models using Off-the-shelf Image Generation and Captioning","created":"2022-08-18","cited_by_count":45},{"id":"2211.01866","title":"ImageNet-X: Understanding Model Mistakes with Factor of Variation Annotations","created":"2022-11-03","cited_by_count":44},{"id":"2107.07430","title":"Wordcraft: a Human-AI Collaborative Editor for Story Writing","created":"2021-07-15","cited_by_count":41},{"id":"2204.02310","title":"Improving Human-AI Partnerships in Child Welfare: Understanding Worker Practices, Challenges, and Desires for Algorithmic Decision Support","created":"2022-04-05","cited_by_count":39},{"id":"2212.02774","title":"Adaptive Testing of Computer Vision Models","created":"2022-12-06","cited_by_count":39},{"id":"2305.07095","title":"Are Machine Rationales (Not) Useful to Humans? Measuring and Improving Human Utility of Free-Text Rationales","created":"2023-05-11","cited_by_count":37},{"id":"2301.06937","title":"Improving Human-AI Collaboration With Descriptions of AI Behavior","created":"2023-01-06","cited_by_count":36},{"id":"2306.12105","title":"Mass-Producing Failures of Multimodal Systems with Language Models","created":"2023-06-21","cited_by_count":36},{"id":"2110.15403","title":"Selective Regression Under Fairness Criteria","created":"2021-10-28","cited_by_count":34},{"id":"2111.11297","title":"Teaching Humans When To Defer to a Classifier via Exemplars","created":"2021-11-22","cited_by_count":29},{"id":"2202.05983","title":"Uncalibrated Models Can Improve Human-AI Collaboration","created":"2022-02-12","cited_by_count":26},{"id":"2005.10960","title":"Misplaced Trust: Measuring the Interference of Machine Learning in Human Decision-Making","created":"2020-05-22","cited_by_count":25},{"id":"2012.15075","title":"Human Evaluation of Spoken vs. Visual Explanations for Open-Domain QA","created":"2020-12-30","cited_by_count":17},{"id":"2210.05839","title":"SEAL : Interactive Tool for Systematic Error Analysis and Labeling","created":"2022-10-11","cited_by_count":15},{"id":"2304.06701","title":"Learning Personalized Decision Support Policies","created":"2023-04-13","cited_by_count":14},{"id":"2102.08540","title":"Intuitively Assessing ML Model Reliability through Example-Based Explanations and Editing Model Inputs","created":"2021-02-17","cited_by_count":9},{"id":"2204.03938","title":"On Distinctive Image Captioning via Comparing and Reweighting","created":"2022-04-08","cited_by_count":7},{"id":"2308.15700","title":"Training Towards Critical Use: Learning to Situate AI Predictions Relative to Human Knowledge","created":"2023-08-30","cited_by_count":6},{"id":"2109.12456","title":"Auditing AI models for Verified Deployment under Semantic Specifications","created":"2021-09-25","cited_by_count":4},{"id":"2305.11888","title":"Taking Advice from ChatGPT","created":"2023-05-11","cited_by_count":3},{"id":"2210.02762","title":"Vision Transformer Based Model for Describing a Set of Images as a Story","created":"2022-10-06","cited_by_count":2},{"id":"2303.09657","title":"ESCAPE: Countering Systematic Errors from Machine's Blind Spots via Interactive Visual Analysis","created":"2023-03-16","cited_by_count":2},{"id":"2210.12112","title":"Describing Sets of Images with Textual-PCA","created":"2022-10-21","cited_by_count":1}],"next_cursor":null}