{"list":"other","total":51,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"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":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848},{"id":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"id":"2305.01210","title":"Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation","created":"2023-05-02","cited_by_count":1391},{"id":"2010.03759","title":"Energy-based Out-of-distribution Detection","created":"2020-10-08","cited_by_count":1299},{"id":"1705.08500","title":"Selective Classification for Deep Neural Networks","created":"2017-05-23","cited_by_count":852},{"id":"2203.14371","title":"MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answering","created":"2022-03-27","cited_by_count":543},{"id":"2103.14749","title":"Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarks","created":"2021-03-26","cited_by_count":395},{"id":"2006.01862","title":"Consistent Estimators for Learning to Defer to an Expert","created":"2020-06-02","cited_by_count":271},{"id":"2006.09462","title":"Selective Question Answering under Domain Shift","created":"2020-06-16","cited_by_count":238},{"id":"2402.13446","title":"Large Language Models for Data Annotation and Synthesis: A Survey","created":"2024-02-21","cited_by_count":205},{"id":"2502.01100","title":"ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning","created":"2025-02-03","cited_by_count":201},{"id":"2108.13487","title":"Want To Reduce Labeling Cost? GPT-3 Can Help","created":"2021-08-30","cited_by_count":196},{"id":"2406.04127","title":"Are We Done with MMLU?","created":"2024-06-06","cited_by_count":194},{"id":"2104.08279","title":"Testing for Outliers with Conformal p-values","created":"2021-04-16","cited_by_count":134},{"id":"2310.15638","title":"CoAnnotating: Uncertainty-Guided Work Allocation between Human and Large Language Models for Data Annotation","created":"2023-10-24","cited_by_count":94},{"id":"2210.01408","title":"Selection by Prediction with Conformal p-values","created":"2022-10-04","cited_by_count":69},{"id":"2405.10301","title":"Conformal Alignment: Knowing When to Trust Foundation Models with Guarantees","created":"2024-05-16","cited_by_count":54},{"id":"2106.02395","title":"DOCTOR: A Simple Method for Detecting Misclassification Errors","created":"2021-06-04","cited_by_count":53},{"id":"2403.03208","title":"Active Statistical Inference","created":"2024-03-05","cited_by_count":50},{"id":"2509.08825","title":"Large Language Model Hacking: Quantifying the Hidden Risks of Using LLMs for Text Annotation","created":"2025-09-10","cited_by_count":50},{"id":"2408.15204","title":"Can Unconfident LLM Annotations Be Used for Confident Conclusions?","created":"2024-08-27","cited_by_count":49},{"id":"2109.00574","title":"Active label cleaning for improved dataset quality under resource constraints","created":"2021-09-01","cited_by_count":44},{"id":"2502.11028","title":"Mind the Confidence Gap: Overconfidence, Calibration, and Distractor Effects in Large Language Models","created":"2025-02-16","cited_by_count":40},{"id":"2310.14230","title":"A comprehensive survey on deep active learning in medical image analysis","created":"2023-10-22","cited_by_count":35},{"id":"2307.09291","title":"Model-free selective inference under covariate shift via weighted conformal p-values","created":"2023-07-18","cited_by_count":29},{"id":"2110.03006","title":"Unsupervised Selective Labeling for More Effective Semi-Supervised Learning","created":"2021-10-06","cited_by_count":27},{"id":"2505.16690","title":"Your Pre-trained LLM is Secretly an Unsupervised Confidence Calibrator","created":"2025-05-22","cited_by_count":20},{"id":"2311.15451","title":"Uncertainty-aware Language Modeling for Selective Question Answering","created":"2023-11-26","cited_by_count":16},{"id":"2208.06685","title":"Adaptive novelty detection with false discovery rate guarantee","created":"2022-08-13","cited_by_count":15},{"id":"2302.07294","title":"Derandomized Novelty Detection with FDR Control via Conformal E-values","created":"2023-02-14","cited_by_count":15},{"id":"2311.15614","title":"FreeAL: Towards Human-Free Active Learning in the Era of Large Language Models","created":"2023-11-27","cited_by_count":14},{"id":"2311.06412","title":"Online multiple testing with e-values","created":"2023-11-10","cited_by_count":12},{"id":"2502.04807","title":"Robust Conformal Outlier Detection under Contaminated Reference Data","created":"2025-02-07","cited_by_count":12},{"id":"2505.00917","title":"Multivariate Conformal Selection","created":"2025-05-01","cited_by_count":8},{"id":"2506.10908","title":"Probably Approximately Correct Labels","created":"2025-06-12","cited_by_count":8},{"id":"2403.12295","title":"Selecting informative conformal prediction sets with false coverage rate control","created":"2024-03-18","cited_by_count":7},{"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},{"id":"2409.16829","title":"Conditional Testing based on Localized Conformal p-values","created":"2024-09-25","cited_by_count":4},{"id":"2501.02703","title":"Full-conformal novelty detection","created":"2025-01-06","cited_by_count":3},{"id":"2508.13838","title":"Online Conformal Selection with Accept-to-Reject Changes","created":"2025-08-19","cited_by_count":3},{"id":"2502.19667","title":"A Conformalized Empirical Bayes Method for Multiple Testing with Side Information","created":"2025-02-27","cited_by_count":2},{"id":"2508.10336","title":"Online selective conformal inference: adaptive scores, convergence rates and optimality","created":"2025-08-14","cited_by_count":2}],"next_cursor":null}