SinoXiv
3
results found
Hallucination in large language model-generated summaries poses a critical safety challenge for knowledge-intensive domains such as Chinese history and culture. Existing faithfulness detection methods...
hallucination safety detection
semantic alignment
Chinese historical and cultural text
faithfulness classification
feature representation
This paper introduces an empirical extension of the Deep Personal Privacy (DPP) framework, a novel paradigm that reconceptualizes privacy as resistance to inference rather than mere control over data ...
Deep Personal Privacy (DPP)
Inference-Based Privacy
Privacy Impedance
Inference Resistance
Large Language Models (LLMs)
Semantic Alignment
Cosine Similarity
Embedding Perturbation
Dual Shifting Transformation
Epistemic Privacy
Privacy Engineering
GDPR
EU AI Act
Cross-modal image-text retrieval aims to precisely match visual content with natural language descriptions, a task pivotal in multimodal understanding. Despite advancements in feature extraction and a...
Cross-Modal Image-Text Retrieval
Multi-Scale Feature Extraction
Adaptive Similarity Fusion
Semantic Complexity
Dynamic Sparse Aggregation
