For years, many chief information officers (CIOs) looked at VMware-to-cloud migrations with a wary pragmatism. Manually mapping dependencies and rewriting legacy apps mid-flight was not an enticing, low-lift proposition for enterprise IT teams. But the calculus for such decisions has changed dramatically in a short period of time. Following recent VMware licensing changes, organizations are […]
A hybrid PSO-AVOA framework for patient-reported drug prioritization with enhanced exploration and exploitation
IntroductionPatient-generated drug reviews are becoming increasingly available and serve as a rich source for computational drug prioritization.MethodsIn this study, we developed a Hybrid Particle Swarm-Enhanced African Vulture Optimisation Algorithm (Hybrid PSO-EAVOA) that fosters the development of better balances between the exploration and exploitation of which the framework uses the improved opposition-based learning, Levy flights, and […]
Redefining psychopathology in the context of digital overload: emerging disorders in the age of information saturation
The accelerating integration of digital technologies with human experience has precipitated profound cognitive, emotional, and behavioral transformations, giving rise to emergent psychopathologies that remain insufficiently addressed by traditional diagnostic taxonomies. This study introduces a novel reconceptualization of mental health in the digital era, delineating four original diagnostic categories: Cognitive Fragmentation and Digital Overload Disorders, Social […]
Stress Testing Factual Consistency Metrics for Long-Document Summarization
arXiv:2511.07689v1 Announce Type: cross Abstract: Evaluating the factual consistency of abstractive text summarization remains a significant challenge, particularly for long documents, where conventional metrics struggle with input length limitations and long-range dependencies. In this work, we systematically evaluate the reliability of six widely used reference-free factuality metrics, originally proposed for short-form summarization, in the long-document […]
FedRW: Efficient Privacy-Preserving Data Reweighting for Enhancing Federated Learning of Language Models
arXiv:2511.07505v1 Announce Type: cross Abstract: Data duplication within large-scale corpora often impedes large language models’ (LLMs) performance and privacy. In privacy-concerned federated learning scenarios, conventional deduplication methods typically rely on trusted third parties to perform uniform deletion, risking loss of informative samples while introducing privacy vulnerabilities. To address these gaps, we propose Federated ReWeighting (FedRW), […]
Private-RAG: Answering Multiple Queries with LLMs while Keeping Your Data Private
arXiv:2511.07637v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) enhances large language models (LLMs) by retrieving documents from an external corpus at inference time. When this corpus contains sensitive information, however, unprotected RAG systems are at risk of leaking private information. Prior work has introduced differential privacy (DP) guarantees for RAG, but only in single-query settings, […]
GRIP: In-Parameter Graph Reasoning through Fine-Tuning Large Language Models
arXiv:2511.07457v1 Announce Type: cross Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in modeling sequential textual data and generalizing across diverse tasks. However, adapting LLMs to effectively handle structural data, such as knowledge graphs or web data, remains a challenging problem. Some approaches adopt complex strategies to convert graphs into text sequences, resulting in […]
KG-DF: A Black-box Defense Framework against Jailbreak Attacks Based on Knowledge Graphs
arXiv:2511.07480v1 Announce Type: cross Abstract: With the widespread application of large language models (LLMs) in various fields, the security challenges they face have become increasingly prominent, especially the issue of jailbreak. These attacks induce the model to generate erroneous or uncontrolled outputs through crafted inputs, threatening the generality and security of the model. Although existing […]
Generating Sketches in a Hierarchical Auto-Regressive Process for Flexible Sketch Drawing Manipulation at Stroke-Level
arXiv:2511.07889v1 Announce Type: cross Abstract: Generating sketches with specific patterns as expected, i.e., manipulating sketches in a controllable way, is a popular task. Recent studies control sketch features at stroke-level by editing values of stroke embeddings as conditions. However, in order to provide generator a global view about what a sketch is going to be […]
Self-Correction Distillation for Structured Data Question Answering
arXiv:2511.07998v1 Announce Type: cross Abstract: Structured data question answering (QA), including table QA, Knowledge Graph (KG) QA, and temporal KG QA, is a pivotal research area. Advances in large language models (LLMs) have driven significant progress in unified structural QA frameworks like TrustUQA. However, these frameworks face challenges when applied to small-scale LLMs since small-scale […]
On the generalization of language models from in-context learning and finetuning: a controlled study
arXiv:2505.00661v3 Announce Type: replace-cross Abstract: Large language models exhibit exciting capabilities, yet can show surprisingly narrow generalization from finetuning. E.g. they can fail to generalize to simple reversals of relations they are trained on, or fail to make simple logical deductions based on trained information. These failures to generalize factual information from fine-tuning can significantly […]
Think Before You Retrieve: Learning Test-Time Adaptive Search with Small Language Models
arXiv:2511.07581v1 Announce Type: new Abstract: Effective information retrieval requires reasoning over partial evidence and refining strategies as information emerges. Yet current approaches fall short: neural retrievers lack reasoning capabilities, large language models (LLMs) provide semantic depth but at prohibitive cost, and query rewriting or decomposition limits improvement to static transformations. As a result, existing methods […]