Adaptive Label Reweighting via Boundary-Aware Meta Learning for Long-Tail Legal Element Recognition
Symmetry · 16.04.2026 · 18 (4) · 664
DOI: 10.3390/sym18040664 ↗Kurz gefasst
Fachartikel in der Zeitschrift Symmetry, online erschienen am 16.04.2026. Verfasst von Kun Han und 2 weiteren Autor:innen. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Legal element recognition, which identifies discrete factual elements in Chinese court judgments to support judicial analysis and case retrieval, faces a severe long-tail challenge: head-to-tail label-frequency ratios exceed 100:1, and over 60% of sentences carry no label, starving rare elements of training signal. Static reweighting methods assign fixed weights prior to training and cannot respond to the model’s evolving confidence; sample-level meta-learning couples all co-occurring label gradients to a single scalar, preventing independent tail-label amplification. We propose BML-Trans, a boundary-aware meta-learning framework that addresses both limitations. A label-wise meta-weighting mechanism maintains per-label gradient weights updated via bilevel hypergradient descent, decoupling tail-label amplification from co-occurring head labels. A boundary-aware meta-set concentrates calibration signal on high-uncertainty, tail-triggering sentences rather than on easy negatives, and a lightweight Multi-Scale Adapter sharpens the warm-up probability estimates on which boundary selection depends. Concretely, BML-Trans achieves an average Avg-F1 of 82.5% on CAIL2019 across the labor, divorce, and loan domains, outperforming the strongest baseline by 1.2 percentage points overall and by up to 5.7 percentage points on tail-label Macro-F1, at only 14% additional training cost. Ablation confirms a cascade dependency among the three components, establishing that the gains are structural rather than incidental to threshold selection or initialization.
Zitieren
APA
Han, K., Han, C., & Zhao, P. (2026). Adaptive Label Reweighting via Boundary-Aware Meta Learning for Long-Tail Legal Element Recognition. Symmetry, 18(4), 664. https://doi.org/10.3390/sym18040664
Vancouver
Han K, Han C, Zhao P. Adaptive Label Reweighting via Boundary-Aware Meta Learning for Long-Tail Legal Element Recognition. Symmetry. 2026;18(4):664. doi:10.3390/sym18040664
BibTeX
@article{Han2026,
author = {Han, Kun and Han, Chengcheng and Zhao, Pengcheng},
title = {Adaptive Label Reweighting via Boundary-Aware Meta Learning for Long-Tail Legal Element Recognition},
journal = {Symmetry},
year = {2026},
volume = {18},
number = {4},
pages = {664},
doi = {10.3390/sym18040664}
}
EUVIMED