World PulseNow
Newsletter

Preference-driven Knowledge Distillation for Few-shot Node Classification

arXiv — cs.LG•Monday, October 27, 2025 at 4:00:00 AM
PositiveArtificial Intelligence
A recent study introduces a novel approach to enhance few-shot node classification in text-attributed graphs using preference-driven knowledge distillation. This method leverages the strengths of graph neural networks and large language models, addressing the challenges posed by limited human-annotated labels and complex node topologies. This advancement is significant as it could improve the efficiency and accuracy of machine learning applications in various fields, making it easier to analyze and interpret complex data structures.
— via World Pulse Now AI Editorial System
Read Original

Was this article worth reading? Share it

Continue Readings
Large language models and research progress: Q&A with an aerospace engineer
Tech Xplore — AI & ML2 days ago
Large language models and research progress: Q&A with an aerospace engineer
NeutralArtificial Intelligence
The rapid expansion of large language models' (LLMs) capabilities—including web search, code execution, data analysis, and hypothesis generation—is outpacing critical reflection on their role in academic research. This raises questions about the implications of LLMs in various fields and the need for a more structured approach to their integration into research methodologies.
Read full article
via Tech Xplore — AI & ML
One Pic is All it Takes: Poisoning Visual Document Retrieval Augmented Generation with a Single Image
arXiv — cs.CV2 days ago
One Pic is All it Takes: Poisoning Visual Document Retrieval Augmented Generation with a Single Image
NegativeArtificial Intelligence
The paper discusses the vulnerabilities of visual document retrieval-augmented generation (VD-RAG) systems to poisoning attacks. By injecting a single adversarial image into the knowledge base, attackers can disrupt both retrieval and generation processes. This highlights the risks associated with integrating visual modalities into retrieval-augmented systems, which are designed to enhance the accuracy of large language models.
Read full article
via arXiv — cs.CV
Unsupervised Discovery of Long-Term Spatiotemporal Periodic Workflows in Human Activities
arXiv — cs.CV2 days ago
Unsupervised Discovery of Long-Term Spatiotemporal Periodic Workflows in Human Activities
PositiveArtificial Intelligence
The study presents a benchmark of 580 multimodal human activity sequences that focus on long-term periodic workflows in human activities, which are often overlooked. It introduces evaluation tasks for unsupervised periodic workflow detection, task completion tracking, and procedural anomaly detection. A lightweight, training-free baseline model is proposed to address the challenges of detecting diverse periodic workflows, particularly in low-contrast patterns.
Read full article
via arXiv — cs.CV
Liars' Bench: Evaluating Lie Detectors for Language Models
arXiv — cs.CL2 days ago
Liars' Bench: Evaluating Lie Detectors for Language Models
NeutralArtificial Intelligence
The article introduces LIARS' BENCH, a comprehensive testbed designed to evaluate lie detection techniques in large language models (LLMs). It consists of 72,863 examples of lies and honest responses generated by four open-weight models across seven datasets. The study reveals that existing lie detection methods often fail to identify certain types of lies, particularly when the model's deception cannot be discerned from the transcript alone, highlighting limitations in current techniques.
Read full article
via arXiv — cs.CL
Mind the Gap: Bridging Prior Shift in Realistic Few-Shot Crop-Type Classification
arXiv — cs.LG2 days ago
Mind the Gap: Bridging Prior Shift in Realistic Few-Shot Crop-Type Classification
PositiveArtificial Intelligence
The article presents a new method called Dirichlet Prior Augmentation (DirPA) aimed at improving few-shot crop-type classification in agriculture. It addresses the issue of class imbalance in labeled datasets, which often leads to a mismatch between training and testing conditions. By simulating an unknown label distribution during model training, DirPA enhances the model's ability to generalize to real-world scenarios, thereby improving classification accuracy.
Read full article
via arXiv — cs.LG
MAQuA: Adaptive Question-Asking for Multidimensional Mental Health Screening using Item Response Theory
arXiv — cs.CL2 days ago
MAQuA: Adaptive Question-Asking for Multidimensional Mental Health Screening using Item Response Theory
PositiveArtificial Intelligence
MAQuA is an adaptive question-asking framework designed for multidimensional mental health screening, leveraging item response theory (IRT) and factor analysis. It optimizes the selection of questions to enhance diagnostic accuracy while reducing the number of queries needed for stable assessments. Empirical results indicate that MAQuA can decrease the number of questions required for score stabilization by 50-87%, significantly improving the efficiency of mental health evaluations.
Read full article
via arXiv — cs.CL
Supervised Contrastive Learning for Few-Shot AI-Generated Image Detection and Attribution
arXiv — cs.CV2 days ago
Supervised Contrastive Learning for Few-Shot AI-Generated Image Detection and Attribution
PositiveArtificial Intelligence
The rapid advancement of generative artificial intelligence has led to the creation of synthetic images that are increasingly difficult to distinguish from real content, challenging digital media integrity. This study proposes a two-stage detection framework utilizing supervised contrastive learning to enhance the detection of AI-generated images. The first stage focuses on extracting discriminative embeddings from images, addressing the generalization challenge in synthetic image detection.
Read full article
via arXiv — cs.CV