{"total":145,"rows":[{"id":"2309.15789","title":"Large Language Model Routing with Benchmark Datasets","created":"2023-09-27","cited_by_count":172,"area":null},{"id":"2206.13089","title":"Agreement-on-the-Line: Predicting the Performance of Neural Networks under Distribution Shift","created":"2022-06-27","cited_by_count":94,"area":null},{"id":"2403.07008","title":"AutoEval Done Right: Using Synthetic Data for Model Evaluation","created":"2024-03-09","cited_by_count":57,"area":"synth"},{"id":"2209.08590","title":"RankFeat: Rank-1 Feature Removal for Out-of-distribution Detection","created":"2022-09-18","cited_by_count":52,"area":null},{"id":"2202.05834","title":"Predicting Out-of-Distribution Error with the Projection Norm","created":"2022-02-11","cited_by_count":50,"area":null},{"id":"2207.13048","title":"Domain Adaptation under Open Set Label Shift","created":"2022-07-26","cited_by_count":32,"area":null},{"id":"2310.16524","title":"Can You Rely on Your Model Evaluation? Improving Model Evaluation with Synthetic Test Data","created":"2023-10-25","cited_by_count":32,"area":null},{"id":"2302.03020","title":"RLSbench: Domain Adaptation Under Relaxed Label Shift","created":"2023-02-06","cited_by_count":30,"area":null},{"id":"2405.05012","title":"The Entropy Enigma: Success and Failure of Entropy Minimization","created":"2024-05-08","cited_by_count":24,"area":null},{"id":"2207.07065","title":"On the Strong Correlation Between Model Invariance and Generalization","created":"2022-07-14","cited_by_count":23,"area":null},{"id":"2411.07681","title":"What Do Learning Dynamics Reveal About Generalization in LLM Reasoning?","created":"2024-11-12","cited_by_count":23,"area":"lr"},{"id":"2302.01094","title":"Confidence and Dispersity Speak: Characterising Prediction Matrix for Unsupervised Accuracy Estimation","created":"2023-02-02","cited_by_count":22,"area":null},{"id":"2403.01874","title":"A Survey on Evaluation of Out-of-Distribution Generalization","created":"2024-03-04","cited_by_count":21,"area":null},{"id":"2305.15640","title":"Characterizing Out-of-Distribution Error via Optimal Transport","created":"2023-05-25","cited_by_count":20,"area":null},{"id":"2202.09931","title":"Deconstructing Distributions: A Pointwise Framework of Learning","created":"2022-02-20","cited_by_count":19,"area":null},{"id":"2209.08436","title":"Estimating and Explaining Model Performance When Both Covariates and Labels Shift","created":"2022-09-18","cited_by_count":19,"area":null},{"id":"2212.02742","title":"A Learning Based Hypothesis Test for Harmful Covariate Shift","created":"2022-12-06","cited_by_count":19,"area":null},{"id":"2310.14586","title":"GNNEvaluator: Evaluating GNN Performance On Unseen Graphs Without Labels","created":"2023-10-23","cited_by_count":17,"area":null},{"id":"2401.12689","title":"Energy-based Automated Model Evaluation","created":"2024-01-23","cited_by_count":17,"area":null},{"id":"2202.01851","title":"A Note on \"Assessing Generalization of SGD via Disagreement\"","created":"2022-02-03","cited_by_count":16,"area":null},{"id":"2306.00312","title":"(Almost) Provable Error Bounds Under Distribution Shift via Disagreement Discrepancy","created":"2023-06-01","cited_by_count":16,"area":null},{"id":"2303.15488","title":"On the Importance of Feature Separability in Predicting Out-Of-Distribution Error","created":"2023-03-27","cited_by_count":15,"area":null},{"id":"2305.18712","title":"Can We Evaluate Domain Adaptation Models Without Target-Domain Labels?","created":"2023-05-30","cited_by_count":14,"area":null},{"id":"2406.07320","title":"A Framework for Efficient Model Evaluation through Stratification, Sampling, and Estimation","created":"2024-06-11","cited_by_count":14,"area":null},{"id":"2302.05018","title":"Predicting Out-of-Distribution Error with Confidence Optimal Transport","created":"2023-02-10","cited_by_count":13,"area":null},{"id":"2301.13371","title":"Demystifying Disagreement-on-the-Line in High Dimensions","created":"2023-01-31","cited_by_count":12,"area":null},{"id":"2310.04414","title":"CIFAR-10-Warehouse: Broad and More Realistic Testbeds in Model Generalization Analysis","created":"2023-10-06","cited_by_count":12,"area":null},{"id":"2403.09953","title":"Online GNN Evaluation Under Test-time Graph Distribution Shifts","created":"2024-03-15","cited_by_count":12,"area":null},{"id":"2205.13577","title":"Understanding new tasks through the lens of training data via exponential tilting","created":"2022-05-26","cited_by_count":11,"area":null},{"id":"2303.13251","title":"A Bag-of-Prototypes Representation for Dataset-Level Applications","created":"2023-03-23","cited_by_count":11,"area":null},{"id":"2305.19570","title":"Online Label Shift: Optimal Dynamic Regret meets Practical Algorithms","created":"2023-05-31","cited_by_count":11,"area":null},{"id":"2310.04941","title":"Test-Time Adaptation Induces Stronger Accuracy and Agreement-on-the-Line","created":"2023-10-07","cited_by_count":11,"area":null},{"id":"2507.08721","title":"Monitoring Risks in Test-Time Adaptation","created":"2025-07-11","cited_by_count":11,"area":null},{"id":"2205.15947","title":"Evaluating Robustness to Dataset Shift via Parametric Robustness Sets","created":"2022-05-31","cited_by_count":10,"area":null},{"id":"2207.09957","title":"Estimating Model Performance under Domain Shifts with Class-Specific Confidence Scores","created":"2022-07-20","cited_by_count":10,"area":null},{"id":"2412.12910","title":"Sequential Harmful Shift Detection Without Labels","created":"2024-12-17","cited_by_count":10,"area":null},{"id":"2201.11676","title":"Monitoring Model Deterioration with Explainable Uncertainty Estimation via Non-parametric Bootstrap","created":"2022-01-27","cited_by_count":9,"area":null},{"id":"2212.10017","title":"Unveiling Code Pre-Trained Models: Investigating Syntax and Semantics Capacities","created":"2022-12-20","cited_by_count":9,"area":null},{"id":"2305.14802","title":"Estimating Large Language Model Capabilities without Labeled Test Data","created":"2023-05-24","cited_by_count":9,"area":null},{"id":"2401.08348","title":"Estimating Model Performance Under Covariate Shift Without Labels","created":"2024-01-16","cited_by_count":9,"area":null},{"id":"2404.01351","title":"AETTA: Label-Free Accuracy Estimation for Test-Time Adaptation","created":"2024-04-01","cited_by_count":9,"area":null},{"id":"2401.03350","title":"Accurate and Scalable Estimation of Epistemic Uncertainty for Graph Neural Networks","created":"2024-01-07","cited_by_count":8,"area":null},{"id":"2405.18979","title":"MANO: Exploiting Matrix Norm for Unsupervised Accuracy Estimation Under Distribution Shifts","created":"2024-05-29","cited_by_count":8,"area":null},{"id":"2407.08649","title":"Confidence-based Estimators for Predictive Performance in Model Monitoring","created":"2024-07-11","cited_by_count":8,"area":null},{"id":"2210.12369","title":"Explanation Shift: Detecting distribution shifts on tabular data via the explanation space","created":"2022-10-22","cited_by_count":7,"area":null},{"id":"2307.00398","title":"ProbVLM: Probabilistic Adapter for Frozen Vision-Language Models","created":"2023-07-01","cited_by_count":7,"area":"mllm"},{"id":"2309.09403","title":"Selecting which Dense Retriever to use for Zero-Shot Search","created":"2023-09-18","cited_by_count":7,"area":null},{"id":"2401.04305","title":"Advancing Deep Active Learning & Data Subset Selection: Unifying Principles with Information-Theory Intuitions","created":"2024-01-09","cited_by_count":7,"area":null},{"id":"2404.01542","title":"Predicting the Performance of Foundation Models via Agreement-on-the-Line","created":"2024-04-02","cited_by_count":7,"area":null},{"id":"2303.08081","title":"Explanation Shift: How Did the Distribution Shift Impact the Model?","created":"2023-03-14","cited_by_count":6,"area":null},{"id":"2308.11111","title":"CAME: Contrastive Automated Model Evaluation","created":"2023-08-22","cited_by_count":6,"area":null},{"id":"2403.13803","title":"Bounding Box Stability against Feature Dropout Reflects Detector Generalization across Environments","created":"2024-03-20","cited_by_count":6,"area":null},{"id":"2406.09908","title":"What Does Softmax Probability Tell Us about Classifiers Ranking Across Diverse Test Conditions?","created":"2024-06-14","cited_by_count":6,"area":null},{"id":"2408.00331","title":"DECIDER: Leveraging Foundation Model Priors for Improved Model Failure Detection and Explanation","created":"2024-08-01","cited_by_count":6,"area":null},{"id":"2506.17442","title":"Keeping Medical AI Healthy and Trustworthy: A Review of Detection and Correction Methods for System Degradation","created":"2025-06-20","cited_by_count":6,"area":null},{"id":"2306.11120","title":"Confidence-Based Model Selection: When to Take Shortcuts for Subpopulation Shifts","created":"2023-06-19","cited_by_count":5,"area":null},{"id":"2312.03318","title":"Complementary Benefits of Contrastive Learning and Self-Training Under Distribution Shift","created":"2023-12-06","cited_by_count":5,"area":null},{"id":"2412.06461","title":"Ranked from Within: Ranking Large Multimodal Models Without Labels","created":"2024-12-09","cited_by_count":5,"area":"mllm"},{"id":"2606.15980","title":"Do Activation Monitors Survive Model Updates? Benchmarking, Predicting, and Repairing Activation-Monitor Staleness","created":"2026-06-14","cited_by_count":5,"area":null},{"id":"2207.02093","title":"Predicting Out-of-Domain Generalization with Neighborhood Invariance","created":"2022-07-05","cited_by_count":4,"area":null},{"id":"2302.08287","title":"Unsupervised Evaluation of Out-of-distribution Detection: A Data-centric Perspective","created":"2023-02-16","cited_by_count":4,"area":null},{"id":"2304.09758","title":"K-means Clustering Based Feature Consistency Alignment for Label-free Model Evaluation","created":"2023-04-17","cited_by_count":4,"area":null},{"id":"2308.16274","title":"Learning Diverse Features in Vision Transformers for Improved Generalization","created":"2023-08-30","cited_by_count":4,"area":null},{"id":"2310.12793","title":"OODRobustBench: a Benchmark and Large-Scale Analysis of Adversarial Robustness under Distribution Shift","created":"2023-10-19","cited_by_count":4,"area":null},{"id":"2408.13648","title":"Explanatory Model Monitoring to Understand the Effects of Feature Shifts on Performance","created":"2024-08-24","cited_by_count":4,"area":null},{"id":"2412.17284","title":"Towards Unsupervised Model Selection for Domain Adaptive Object Detection","created":"2024-12-23","cited_by_count":4,"area":null},{"id":"2501.11866","title":"Evaluating multiple models using labeled and unlabeled data","created":"2025-01-21","cited_by_count":4,"area":null},{"id":"2501.19032","title":"Error Slice Discovery via Manifold Compactness","created":"2025-01-31","cited_by_count":4,"area":null},{"id":"2505.22356","title":"Suitability Filter: A Statistical Framework for Classifier Evaluation in Real-World Deployment Settings","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2206.10697","title":"Performance Prediction Under Dataset Shift","created":"2022-06-21","cited_by_count":3,"area":null},{"id":"2210.04166","title":"Test-time Recalibration of Conformal Predictors Under Distribution Shift Based on Unlabeled Examples","created":"2022-10-09","cited_by_count":3,"area":null},{"id":"2302.00775","title":"Model Monitoring and Robustness of In-Use Machine Learning Models: Quantifying Data Distribution Shifts Using Population Stability Index","created":"2023-02-01","cited_by_count":3,"area":null},{"id":"2303.08040","title":"Beyond Demographic Parity: Redefining Equal Treatment","created":"2023-03-14","cited_by_count":3,"area":null},{"id":"2307.10062","title":"Unsupervised Accuracy Estimation of Deep Visual Models using Domain-Adaptive Adversarial Perturbation without Source Samples","created":"2023-07-19","cited_by_count":3,"area":null},{"id":"2401.08909","title":"Leveraging Gradients for Unsupervised Accuracy Estimation under Distribution Shift","created":"2024-01-17","cited_by_count":3,"area":null},{"id":"2509.22506","title":"Representing LLMs in Prompt Semantic Task Space","created":"2025-09-26","cited_by_count":3,"area":null},{"id":"2512.04571","title":"Temp-SCONE: A Novel Out-of-Distribution Detection and Domain Generalization Framework for Wild Data with Temporal Shift","created":"2025-12-04","cited_by_count":3,"area":null},{"id":"2603.18481","title":"T-QPM: Enabling Temporal Out-Of-Distribution Detection and Domain Generalization for Vision-Language Models in Open-World","created":"2026-03-19","cited_by_count":3,"area":"mllm"},{"id":"2207.05796","title":"Estimating Test Performance for AI Medical Devices under Distribution Shift with Conformal Prediction","created":"2022-07-12","cited_by_count":2,"area":null},{"id":"2207.13341","title":"Towards Clear Expectations for Uncertainty Estimation","created":"2022-07-27","cited_by_count":2,"area":null},{"id":"2212.04461","title":"Leveraging Unlabeled Data to Track Memorization","created":"2022-12-08","cited_by_count":2,"area":null},{"id":"2308.07223","title":"Distance Matters For Improving Performance Estimation Under Covariate Shift","created":"2023-08-14","cited_by_count":2,"area":null},{"id":"2309.05619","title":"Effective Proxy for Human Labeling: Ensemble Disagreement Scores in Large Language Models for Industrial NLP","created":"2023-09-11","cited_by_count":2,"area":null},{"id":"2410.02735","title":"OOD-Chameleon: Is Algorithm Selection for OOD Generalization Learnable?","created":"2024-10-03","cited_by_count":2,"area":null},{"id":"2410.05980","title":"Generalizing to any diverse distribution: uniformity, gentle finetuning and rebalancing","created":"2024-10-08","cited_by_count":2,"area":null},{"id":"2505.05295","title":"Performance Estimation in Binary Classification Using Calibrated Confidence","created":"2025-05-08","cited_by_count":2,"area":null},{"id":"2505.11380","title":"On the Interconnections of Calibration, Quantification, and Classifier Accuracy Prediction under Dataset Shift","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2507.12894","title":"LanePerf: a Performance Estimation Framework for Lane Detection","created":"2025-07-17","cited_by_count":2,"area":null},{"id":"2601.09001","title":"Entropy Sentinel: Probing Entropy Traces for LLM Monitoring","created":"2026-01-13","cited_by_count":2,"area":null},{"id":"2603.07841","title":"An Efficient and Effective Evaluator for Text2SQL Models on Unseen and Unlabeled Data","created":"2026-03-08","cited_by_count":2,"area":null},{"id":"2606.11949","title":"Online Shift Detection and Conformal Adaptation for Deployed Safety Classifiers","created":"2026-06-10","cited_by_count":2,"area":"lr"},{"id":"2303.05331","title":"Adaptive Calibrator Ensemble for Model Calibration under Distribution Shift","created":"2023-03-09","cited_by_count":1,"area":null},{"id":"2306.01206","title":"Estimating Semantic Similarity between In-Domain and Out-of-Domain Samples","created":"2023-06-01","cited_by_count":1,"area":null},{"id":"2311.09422","title":"Predicting generalization performance with correctness discriminators","created":"2023-11-15","cited_by_count":1,"area":null},{"id":"2311.13959","title":"RankFeat&RankWeight: Rank-1 Feature/Weight Removal for Out-of-distribution Detection","created":"2023-11-23","cited_by_count":1,"area":null},{"id":"2312.08033","title":"Beyond Top-Class Agreement: Using Divergences to Forecast Performance under Distribution Shift","created":"2023-12-13","cited_by_count":1,"area":null},{"id":"2408.01301","title":"A Decision-driven Methodology for Designing Uncertainty-aware AI Self-Assessment","created":"2024-08-02","cited_by_count":1,"area":null},{"id":"2408.02209","title":"Source-Free Domain-Invariant Performance Prediction","created":"2024-08-05","cited_by_count":1,"area":null},{"id":"2408.13738","title":"Poor-Supervised Evaluation for SuperLLM via Mutual Consistency","created":"2024-08-25","cited_by_count":1,"area":null},{"id":"2412.20682","title":"Learning to Rank Pre-trained Vision-Language Models for Downstream Tasks","created":"2024-12-30","cited_by_count":1,"area":"mllm"}],"next_cursor":"100"}