{"total":34,"rows":[{"id":"2211.02570","title":"The 'Problem' of Human Label Variation: On Ground Truth in Data, Modeling and Evaluation","created":"2022-11-04","cited_by_count":139,"area":null},{"id":"2202.00666","title":"Locally Typical Sampling","created":"2022-02-01","cited_by_count":111,"area":null},{"id":"2307.03749","title":"On the Efficacy of Sampling Adapters","created":"2023-07-07","cited_by_count":17,"area":null},{"id":"2108.13555","title":"Adaptive Label Smoothing To Regularize Large-Scale Graph Training","created":"2021-08-30","cited_by_count":12,"area":null},{"id":"2208.13764","title":"Temporal Label Smoothing for Early Event Prediction","created":"2022-08-29","cited_by_count":12,"area":null},{"id":"2103.10291","title":"Smoothing and Shrinking the Sparse Seq2Seq Search Space","created":"2021-03-18","cited_by_count":11,"area":null},{"id":"2105.07144","title":"A Cognitive Regularizer for Language Modeling","created":"2021-05-15","cited_by_count":11,"area":null},{"id":"2207.03066","title":"Device-Cloud Collaborative Recommendation via Meta Controller","created":"2022-07-07","cited_by_count":10,"area":null},{"id":"2106.07250","title":"Unified Interpretation of Softmax Cross-Entropy and Negative Sampling: With Case Study for Knowledge Graph Embedding","created":"2021-06-14","cited_by_count":7,"area":null},{"id":"2110.06961","title":"Language Modelling via Learning to Rank","created":"2021-10-13","cited_by_count":7,"area":null},{"id":"2310.16499","title":"Data Optimization in Deep Learning: A Survey","created":"2023-10-25","cited_by_count":6,"area":null},{"id":"2403.17240","title":"The Role of $n$-gram Smoothing in the Age of Neural Networks","created":"2024-03-25","cited_by_count":6,"area":null},{"id":"2212.04205","title":"DC-MBR: Distributional Cooling for Minimum Bayesian Risk Decoding","created":"2022-12-08","cited_by_count":4,"area":null},{"id":"2507.07780","title":"Where are we with calibration under dataset shift in image classification?","created":"2025-07-10","cited_by_count":4,"area":null},{"id":"2203.02889","title":"Focus on the Target's Vocabulary: Masked Label Smoothing for Machine Translation","created":"2022-03-06","cited_by_count":3,"area":null},{"id":"2110.13231","title":"Improving the Diversity of Unsupervised Paraphrasing with Embedding Outputs","created":"2021-10-25","cited_by_count":2,"area":null},{"id":"2205.00659","title":"The Implicit Length Bias of Label Smoothing on Beam Search Decoding","created":"2022-05-02","cited_by_count":2,"area":null},{"id":"2209.10058","title":"Mutual Information Learned Classifiers: an Information-theoretic Viewpoint of Training Deep Learning Classification Systems","created":"2022-09-21","cited_by_count":2,"area":null},{"id":"2305.08501","title":"Label Smoothing is Robustification against Model Misspecification","created":"2023-05-15","cited_by_count":2,"area":null},{"id":"2311.15395","title":"ConstraintMatch for Semi-constrained Clustering","created":"2023-11-26","cited_by_count":2,"area":null},{"id":"2312.10087","title":"Revisiting the Entropy Semiring for Neural Speech Recognition","created":"2023-12-13","cited_by_count":2,"area":null},{"id":"2407.12211","title":"On the Calibration of Epistemic Uncertainty: Principles, Paradoxes and Conflictual Loss","created":"2024-07-16","cited_by_count":2,"area":null},{"id":"2102.05131","title":"Label Smoothed Embedding Hypothesis for Out-of-Distribution Detection","created":"2021-02-09","cited_by_count":1,"area":null},{"id":"2110.02054","title":"NoiER: An Approach for Training more Reliable Fine-TunedDownstream Task Models","created":"2021-08-29","cited_by_count":1,"area":null},{"id":"2208.03684","title":"Preserving Fine-Grain Feature Information in Classification via Entropic Regularization","created":"2022-08-07","cited_by_count":1,"area":null},{"id":"2209.09857","title":"Fine-grained Classification of Solder Joints with {\\alpha}-skew Jensen-Shannon Divergence","created":"2022-09-20","cited_by_count":0,"area":null},{"id":"2210.01000","title":"Mutual Information Learned Classifiers: an Information-theoretic Viewpoint of Training Deep Learning Classification Systems","created":"2022-10-03","cited_by_count":0,"area":null},{"id":"2305.04971","title":"LABO: Towards Learning Optimal Label Regularization via Bi-level Optimization","created":"2023-05-08","cited_by_count":0,"area":null},{"id":"2408.17010","title":"Improving Time Series Classification with Representation Soft Label Smoothing","created":"2024-08-30","cited_by_count":0,"area":null},{"id":"2504.06037","title":"Confidence Regularized Masked Language Modeling using Text Length","created":"2025-04-08","cited_by_count":0,"area":null},{"id":"2508.14077","title":"Label Smoothing is a Pragmatic Information Bottleneck","created":"2025-08-12","cited_by_count":0,"area":null},{"id":"2510.02107","title":"PENEX: AdaBoost-Inspired Neural Network Regularization","created":"2025-10-02","cited_by_count":0,"area":null},{"id":"2609.00816","title":"Can Scene Text Recognition Read Rare Compositions?","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2610.13693","title":"Calibration in One Go: Jointly Learning Accurate and Calibrated Neural Networks","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}