LANE: Label-Aware Noise Elimination for Fine-Grained Text Classification

Tiberiu Sosea, Cornelia CarageaSubmission to ICLR 2025 · Rejected

Abstract

We propose Label-Aware Noise Elimination (LANE), a new approach that improves the robustness of deep learning models in fine-grained text classification when trained under increased label noise. LANE leverages the semantic relations between classes and monitors the training dynamics of the model on each training example to dynamically lower the importance of training examples that may have noisy labels. We test the effectiveness of LANE in fine-grained text classification and benchmark our approach on a wide variety of datasets with various number of classes and various amounts of label noise. LANE considerably outperforms strong baselines on all datasets, obtaining significant improvements ranging from an average improvement of 2.4% in F1 on manually annotated datasets to a considerable average improvement of 4.5% F1 on datasets with injected noisy labels. We carry out comprehensive analyses of LANE and identify the key components that lead to its success.
BibTeX
@inproceedings{sosea2026lane,
  author = {Tiberiu Sosea and Cornelia Caragea},
  title = {{LANE: Label-Aware Noise Elimination for Fine-Grained Text Classification}},
  booktitle = {International Conference on Learning Representations},
  year = {2026},
  url = {https://openreview.net/forum?id=PuayLKdrFz},
}
Figure