探索全球前沿学术脉络

Disentangling Hallucinations: Orthogonal Semantic Projection for Robust Interpretability

As Vision-Language Models are increasingly deployed in safety-critical applications, the trustworthiness of their explanations becomes crucial. Explainable AI (XAI) methods for Vision-Language Models often suffer from semantic hallucination, where attribution maps highlight prominent image regions even when prompted with incorrect text descriptions (e.g., highlighting a dog when prompted ``cat''). Although this problem is widespread, a formal mathematical analysis of XAI methods and CLIP embeddings is largely missing in the literature. We demonstrate that this phenomenon is not specific to a single architecture but is a fundamental consequence of Linear Semantic Leakage in high-dimensional embedding spaces. We propose a unified theoretical framework, Linear Semantic Attribution (LSA), which generalizes across discriminative methods. We introduce OSP, a geometric intervention that utilizes the residual property of OMP to disentangle unique semantic signals from shared concepts. We prove theoretically and demonstrate empirically that OSP minimizes hallucination by orthogonalizing the query vector against distractor concepts, rendering the attribution model blind to shared features while preserving fidelity for correct prompts. Our code is available at: https://github.com/emirhanbilgic/Orthogonal-Semantic-Projection

Evaluation of AI-Generated Synthetic Data for Clinical Research in Secondary Cardiovascular Prevention among Dyslipidemia Patients

Background: Access to high-quality clinical data is essential for advancing medical research and developing effective medical statistical and Artificial Intelligence models. However, privacy regulations and logistical barriers often hinder timely access to real-world data. Synthetic data offer a promising solution, preserving the statistical characteristics of original datasets while protecting patient privacy. Objectives: This study investigates the use of synthetic data for secondary cardiovascular prevention in patients with dyslipidemia, using two real-world datasets from Centro Cardiologico Monzino. Methods: Given the high dimensionality and limited sample size of the datasets, we employed a custom generative framework based on Large Language Models (LLMs). Pre-trained LLMs were fine-tuned on original clinical records to synthesize tabular data replicating source-data distributions. Fine-tuning was performed within the Centro Cardiologico Monzino's secure infrastructure to ensure data sovereignty. We evaluate clinical utility and privacy using fidelity and privacy metrics, identifying the optimal generative model and benchmarking against traditional anonymization methods. Results: Synthetic data achieved a superior trade-off than classically anonymized datasets. Real and synthetic datasets showed strong agreement, with significant distributional differences limited to few variables. Models trained on synthetic data replicated key associations from the original dataset, including therapy modification and creatine phosphokinase as predictors of SAMS, and pharmacological intensity as the main driver of LDL-C reduction. Conclusions: Results support the feasibility of using synthetic data as a proxy for real-world datasets in exploratory analyses and model development. Despite slight attenuation of some effect sizes, preserved clinical relationships reinforce the validity of synthetic data in medical research.