{"total":53,"rows":[{"id":"2309.15789","title":"Large Language Model Routing with Benchmark Datasets","created":"2023-09-27","cited_by_count":172,"area":null},{"id":"2201.04234","title":"Leveraging Unlabeled Data to Predict Out-of-Distribution Performance","created":"2022-01-11","cited_by_count":145,"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":"2202.05834","title":"Predicting Out-of-Distribution Error with the Projection Norm","created":"2022-02-11","cited_by_count":50,"area":null},{"id":"2302.03020","title":"RLSbench: Domain Adaptation Under Relaxed Label Shift","created":"2023-02-06","cited_by_count":30,"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":"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":"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":"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":"2205.12702","title":"Detecting Label Errors by using Pre-Trained Language Models","created":"2022-05-25","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":"2301.13371","title":"Demystifying Disagreement-on-the-Line in High Dimensions","created":"2023-01-31","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":"2112.00694","title":"Label-Free Model Evaluation with Semi-Structured Dataset Representations","created":"2021-12-01","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":"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":"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":"2309.09403","title":"Selecting which Dense Retriever to use for Zero-Shot Search","created":"2023-09-18","cited_by_count":7,"area":null},{"id":"2310.14814","title":"Leveraging Ensemble Diversity for Robust Self-Training in the Presence of Sample Selection Bias","created":"2023-10-23","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":"2209.08443","title":"HAPI: A Large-scale Longitudinal Dataset of Commercial ML API Predictions","created":"2022-09-18","cited_by_count":6,"area":null},{"id":"2210.06776","title":"Improving the Reliability for Confidence Estimation","created":"2022-10-13","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":"2404.08517","title":"Online Safety Analysis for LLMs: a Benchmark, an Assessment, and a Path Forward","created":"2024-04-12","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":"2111.11053","title":"DAPPER: Label-Free Performance Estimation after Personalization for Heterogeneous Mobile Sensing","created":"2021-11-22","cited_by_count":4,"area":null},{"id":"2302.02628","title":"Trust, but Verify: Using Self-Supervised Probing to Improve Trustworthiness","created":"2023-02-06","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":"2412.17284","title":"Towards Unsupervised Model Selection for Domain Adaptive Object Detection","created":"2024-12-23","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":"2304.03870","title":"ASPEST: Bridging the Gap Between Active Learning and Selective Prediction","created":"2023-04-07","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":"2312.05589","title":"A Review of Hybrid and Ensemble in Deep Learning for Natural Language Processing","created":"2023-12-09","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":"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":"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":"2601.09001","title":"Entropy Sentinel: Probing Entropy Traces for LLM Monitoring","created":"2026-01-13","cited_by_count":2,"area":null},{"id":"2407.14306","title":"Label-Free Model Failure Detection for Lidar-based Point Cloud Segmentation","created":"2024-07-19","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":"2506.14978","title":"ODD: Overlap-aware Estimation of Model Performance under Distribution Shift","created":"2025-06-17","cited_by_count":1,"area":null},{"id":"2510.02956","title":"Confidence and Dispersity as Signals: Unsupervised Model Evaluation and Ranking","created":"2025-10-03","cited_by_count":1,"area":null},{"id":"2510.27263","title":"ODP-Bench: Benchmarking Out-of-Distribution Performance Prediction","created":"2025-10-31","cited_by_count":1,"area":null},{"id":"2605.23595","title":"Learning to Evaluate: Cost-Effective Model Evaluation on Unlabeled Data with Meta-Learning","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2303.13589","title":"On the Efficacy of Generalization Error Prediction Scoring Functions","created":"2023-03-23","cited_by_count":0,"area":null}],"next_cursor":null}