Tag
The paper presents Multi-Label Agreement (MLA), a flexible framework for evaluating inter-annotator reliability in multi-label annotation tasks using pairwise Hamming agreement with multiple normalization options, along with a Python implementation.
CARing 框架通过组合式语义ID和覆盖感知的强化学习奖励，优化大语言模型在多标签下次就诊诊断预测中的推理轨迹， 在 MIMIC-III/IV 数据集上超越所有 EHR 训练基线。
The paper introduces a weakly supervised multi-label proportion learning framework for sea-ice type prediction using SAR imagery and multimodal data, achieving significant accuracy improvements over supervised baselines.
XGBoost has been updated to support multi-class and multi-label problems without the need to train separate models for each class or label, introducing the Vector-Leaf Model.
This paper proposes MSB-GFM, a multi-semantic basis graph foundation model for cross-domain multi-label node classification, addressing semantic entanglement by representing nodes as adaptive compositions of semantic bases.
Proposes an analytic federated learning framework that requires only one or two communication rounds for multi-label medical image classification under task heterogeneity, outperforming existing methods on ChestXray14 by up to 18.44 BACC and 13.24 AUC points.
The paper proposes Label Influence Propagation (LIP), a model that analyzes and propagates label influences in graph neural networks for multi-label node classification, consistently outperforming state-of-the-art methods.
This paper proposes a zero-shot multi-label topic classification framework enhanced with per-article knowledge graphs, comparing four base variants and their graph-augmented counterparts across fifteen LLMs and eight datasets. The study finds that keyword-enhanced classification performs best, and graph augmentation improves small models but degrades performance in larger ones.
Introduces TADDLE, a tool-augmented agent for detecting deficient LLM-generated peer reviews, along with an expert-annotated benchmark of 1,800 reviews on 50 ICLR 2025 papers. The system decomposes detection into four specialized analysis tools and uses two-stage semi-supervised learning for binary and multi-label classification.
This paper proposes a retrieval-based approach for multi-label legal annotation that uses frozen embedding models to retrieve labels via k-nearest neighbors, achieving competitive accuracy, high data efficiency, and eliminating label hallucination by design.