{"list":"other","total":63,"rows":[{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1610.02136","title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","created":"2016-10-07","cited_by_count":2385},{"id":"1901.07031","title":"CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison","created":"2019-01-21","cited_by_count":1423},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"2010.03759","title":"Energy-based Out-of-distribution Detection","created":"2020-10-08","cited_by_count":1299},{"id":"2310.11324","title":"Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting","created":"2023-10-17","cited_by_count":817},{"id":"2110.11334","title":"Generalized Out-of-Distribution Detection: A Survey","created":"2021-10-21","cited_by_count":802},{"id":"2106.11959","title":"Revisiting Deep Learning Models for Tabular Data","created":"2021-06-22","cited_by_count":740},{"id":"2110.01889","title":"Deep Neural Networks and Tabular Data: A Survey","created":"2021-10-05","cited_by_count":491},{"id":"2211.08411","title":"Large Language Models Struggle to Learn Long-Tail Knowledge","created":"2022-11-15","cited_by_count":458},{"id":"1802.03916","title":"Detecting and Correcting for Label Shift with Black Box Predictors","created":"2018-02-12","cited_by_count":366},{"id":"1812.02849","title":"A Survey of Unsupervised Deep Domain Adaptation","created":"2018-12-06","cited_by_count":361},{"id":"1708.02072","title":"Measuring Catastrophic Forgetting in Neural Networks","created":"2017-08-07","cited_by_count":360},{"id":"2303.15361","title":"A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts","created":"2023-03-27","cited_by_count":359},{"id":"2302.12813","title":"Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback","created":"2023-02-24","cited_by_count":353},{"id":"2102.09508","title":"Domain Adaptation for Medical Image Analysis: A Survey","created":"2021-02-18","cited_by_count":352},{"id":"2309.01431","title":"Benchmarking Large Language Models in Retrieval-Augmented Generation","created":"2023-09-04","cited_by_count":312},{"id":"1901.07441","title":"PadChest: A large chest x-ray image dataset with multi-label annotated reports","created":"2019-01-22","cited_by_count":309},{"id":"2307.09009","title":"How is ChatGPT's behavior changing over time?","created":"2023-07-18","cited_by_count":270},{"id":"1610.06545","title":"Revisiting Classifier Two-Sample Tests","created":"2016-10-20","cited_by_count":268},{"id":"2103.12051","title":"SSD: A Unified Framework for Self-Supervised Outlier Detection","created":"2021-03-22","cited_by_count":264},{"id":"1810.11953","title":"Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift","created":"2018-10-29","cited_by_count":243},{"id":"2002.02770","title":"A Survey on Causal Inference","created":"2020-02-05","cited_by_count":202},{"id":"2306.09301","title":"OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detection","created":"2023-06-15","cited_by_count":179},{"id":"2307.15343","title":"Med-HALT: Medical Domain Hallucination Test for Large Language Models","created":"2023-07-28","cited_by_count":157},{"id":"2410.12405","title":"ProSA: Assessing and Understanding the Prompt Sensitivity of LLMs","created":"2024-10-16","cited_by_count":149},{"id":"2201.04234","title":"Leveraging Unlabeled Data to Predict Out-of-Distribution Performance","created":"2022-01-11","cited_by_count":145},{"id":"2002.06716","title":"Predicting trends in the quality of state-of-the-art neural networks without access to training or testing data","created":"2020-02-17","cited_by_count":115},{"id":"2406.04836","title":"Revisiting Catastrophic Forgetting in Large Language Model Tuning","created":"2024-06-07","cited_by_count":99},{"id":"2211.14238","title":"Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Time","created":"2022-11-25","cited_by_count":90},{"id":"2312.07577","title":"Benchmarking Distribution Shift in Tabular Data with TableShift","created":"2023-12-10","cited_by_count":66},{"id":"2406.06391","title":"Towards Lifelong Learning of Large Language Models: A Survey","created":"2024-06-10","cited_by_count":64},{"id":"2202.01034","title":"Diagnosing failures of fairness transfer across distribution shift in real-world medical settings","created":"2022-02-02","cited_by_count":45},{"id":"2110.06177","title":"Tracking the risk of a deployed model and detecting harmful distribution shifts","created":"2021-10-12","cited_by_count":40},{"id":"2502.06065","title":"Benchmarking Prompt Sensitivity in Large Language Models","created":"2025-02-09","cited_by_count":38},{"id":"2405.03000","title":"MedAdapter: Efficient Test-Time Adaptation of Large Language Models towards Medical Reasoning","created":"2024-05-05","cited_by_count":36},{"id":"2203.05574","title":"On-the-Fly Test-time Adaptation for Medical Image Segmentation","created":"2022-03-10","cited_by_count":34},{"id":"2310.07343","title":"How Do Large Language Models Capture the Ever-changing World Knowledge? A Review of Recent Advances","created":"2023-10-11","cited_by_count":33},{"id":"2205.13723","title":"DLTTA: Dynamic Learning Rate for Test-time Adaptation on Cross-domain Medical Images","created":"2022-05-27","cited_by_count":28},{"id":"2405.17419","title":"MultiOOD: Scaling Out-of-Distribution Detection for Multiple Modalities","created":"2024-05-27","cited_by_count":28},{"id":"1910.06239","title":"Two-sample Testing Using Deep Learning","created":"2019-10-14","cited_by_count":27},{"id":"1911.07421","title":"Deep Verifier Networks: Verification of Deep Discriminative Models with Deep Generative Models","created":"2019-11-18","cited_by_count":25},{"id":"2404.06362","title":"Test-Time Adaptation with SaLIP: A Cascade of SAM and CLIP for Zero shot Medical Image Segmentation","created":"2024-04-09","cited_by_count":25},{"id":"2305.12741","title":"Coswara: A respiratory sounds and symptoms dataset for remote screening of SARS-CoV-2 infection","created":"2023-05-22","cited_by_count":22},{"id":"2110.14019","title":"Reliable and Trustworthy Machine Learning for Health Using Dataset Shift Detection","created":"2021-10-26","cited_by_count":21},{"id":"2310.20271","title":"From Denoising Training to Test-Time Adaptation: Enhancing Domain Generalization for Medical Image Segmentation","created":"2023-10-31","cited_by_count":20},{"id":"2111.13657","title":"Amazon SageMaker Model Monitor: A System for Real-Time Insights into Deployed Machine Learning Models","created":"2021-11-26","cited_by_count":16},{"id":"2104.13621","title":"MLDemon: Deployment Monitoring for Machine Learning Systems","created":"2021-04-28","cited_by_count":14},{"id":"2110.08205","title":"Fast Online Changepoint Detection via Functional Pruning CUSUM statistics","created":"2021-10-15","cited_by_count":10},{"id":"2210.13027","title":"E-Valuating Classifier Two-Sample Tests","created":"2022-10-24","cited_by_count":10},{"id":"2412.12910","title":"Sequential Harmful Shift Detection Without Labels","created":"2024-12-17","cited_by_count":10},{"id":"2209.11890","title":"DomainATM: Domain Adaptation Toolbox for Medical Data Analysis","created":"2022-09-24","cited_by_count":9},{"id":"2411.08870","title":"The Limited Impact of Medical Adaptation of Large Language and Vision-Language Models","created":"2024-11-13","cited_by_count":9},{"id":"2411.00186","title":"Self-Healing Machine Learning: A Framework for Autonomous Adaptation in Real-World Environments","created":"2024-10-31","cited_by_count":8},{"id":"2407.06852","title":"TE-SSL: Time and Event-aware Self Supervised Learning for Alzheimer's Disease Progression Analysis","created":"2024-07-09","cited_by_count":5},{"id":"2411.10701","title":"Diffusion-based Layer-wise Semantic Reconstruction for Unsupervised Out-of-Distribution Detection","created":"2024-11-16","cited_by_count":5},{"id":"2207.11290","title":"TRUST-LAPSE: An Explainable and Actionable Mistrust Scoring Framework for Model Monitoring","created":"2022-07-22","cited_by_count":3},{"id":"2506.15404","title":"NERO: Explainable Out-of-Distribution Detection with Neuron-level Relevance","created":"2025-06-18","cited_by_count":3},{"id":"2305.02474","title":"MLHOps: Machine Learning for Healthcare Operations","created":"2023-05-04","cited_by_count":2},{"id":"2312.04546","title":"Adversarial Learning for Feature Shift Detection and Correction","created":"2023-12-07","cited_by_count":2},{"id":"2401.14093","title":"McUDI: Model-Centric Unsupervised Degradation Indicator for Failure Prediction AIOps Solutions","created":"2024-01-25","cited_by_count":1}],"next_cursor":null}