The paper proposes a zero-shot multi-label topic classification framework and finds that while knowledge graph augmentation improves performance for smaller language models, it offers diminishing retu…

This paper comparatively analyzes two automatic label error detection methods, Confident Learning and Dataset Cartography, demonstrating that targeted data filtering significantly improves model perfo…

FedMPT introduces a novel federated learning framework for Multi-Label Recognition (MLR) using Vision-Language Models (VLMs) by leveraging generalizable conditions to mitigate label overfitting and im…

HASTE introduces group-shared fixed fan-in sparsity for multi-label classification, achieving significant wall-clock speedups (up to 25x in backward pass) by enabling efficient GPU execution while mai…

The paper proposes a robust, multi-stage pipeline combining rule-based classification and machine learning to map noisy retail product names to standardized consumption categories, finding that simple…

The paper introduces a novel, scalable framework to monitor and classify dataset usage within research literature, addressing the current lack of infrastructure for tracking data citations.

The paper systematically compares multimodal transformer and LLM approaches for document type classification, finding that specialized multimodal Transformers outperform LLM-based models, especially w…

The paper proposes pretraining a Perceiver-style in-context learner on synthetic data to solve Multiple Instance Learning (MIL) tasks efficiently in the low-label regime.

This paper proposes a lightweight encoder-based MEL solution called FAST-MEL that meets three objectives: high linking accuracy, computational efficiency, and storage efficiency.

The paper introduces an Item Response Theory (IRT)-based indicator that effectively identifies likely mislabeled items in existing LLM benchmarks, revealing systematic errors in labeling and model spe…

The paper formalizes the concept of calibration for probabilistic label ranking, demonstrating that popular models are often poorly calibrated and that calibration captures a meaningful quality dimens…

The paper systematically evaluates concept-based explainability in MLLMs, finding that forcing models to generate formal explanations degrades predictive accuracy, suggesting that explaining is genuin…

This paper addresses the challenge of achieving optimal fairness and accuracy simultaneously in multi-class classification by proposing novel in-processing and post-processing algorithms that converge…

EvoPool introduces an evolutionary multi-agent framework that efficiently generates high-quality, specialized supervision labels, significantly outperforming LLM annotation baselines across complex, l…

The paper proposes MIMO, a two-stage framework that improves Multilingual Information Retrieval (MLIR) by stabilizing cross-lingual alignment and enhancing retrieval discrimination using a combination…

The paper presents BEATS, a human-in-the-loop LLM framework for bootstrapping product attribute taxonomies from scratch.

The paper proposes a zero-label malware family classification framework that uses a weighted hierarchical ensemble of large language models (LLMs) to classify malware without requiring labeled trainin…

This paper proposes a unified evaluation framework for hate speech detection that systematically assesses model performance and explainability across various label and rationale representation spaces,…

The paper introduces BioConCal, a supervised scoring mechanism that evaluates biomedical NER candidates surfaced by multiple LLMs, significantly improving the quality of the candidate pool for human c…

This systematic mapping survey reviews label-efficient approaches for code vulnerability detection, synthesizing five paradigm families and providing a decision guide to navigate trade-offs.