arXiv:2603.18373v2 Announce Type: replace-cross Abstract: When VLMs answer correctly, do they genuinely rely on visual information or exploit language shortcuts? We introduce the Tri-Layer Diagnostic Framework, which disentangles hallucination sources via three metrics: Latent Anomaly Detection (perceptual awareness), Visual Necessity Score (visual dependency, measured via KL divergence), and Competition Score (conflict between visual grounding and […]
Agentic Explainability at Scale: Between Corporate Fears and XAI Needs
arXiv:2604.14984v1 Announce Type: cross Abstract: As companies enter the race for agentic AI adoption, fears surface around agentic autonomy and its subsequent risks. These fears compound as companies scale their agentic AI adoption with low-code applications, without a comparable scaling in their governance processes and expertise resulting in a phenomenon known as “Agent Sprawl”. While […]
Disentangled Dual-Branch Graph Learning for Conversational Emotion Recognition
arXiv:2604.14204v1 Announce Type: cross Abstract: Multimodal emotion recognition in conversations aims to infer utterance-level emotions by jointly modeling textual, acoustic, and visual cues within context. Despite recent progress, key challenges remain, including redundant cross-modal information, imperfect semantic alignment, and insufficient modeling of high-order speaker interactions. To address these issues, we propose a framework that combines […]
Adaptive Query Routing: A Tier-Based Framework for Hybrid Retrieval Across Financial, Legal, and Medical Documents
arXiv:2604.14222v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) has become the standard paradigm for grounding Large Language Model outputs in external knowledge. Lumer et al. [1] presented the first systematic evaluation comparing vector-based agentic RAG against hierarchical node-based reasoning systems for financial document QA across 1,200 SEC filings, finding vector-based systems achieved a 68% win […]
Combining Bayesian and Frequentist Inference for Laboratory-Specific Performance Guarantees in Copy Number Variation Detection
arXiv:2604.14305v1 Announce Type: cross Abstract: Targeted amplicon panels are widely used in oncology diagnostics, but providing per-gene performance guarantees for copy number variant (CNV) detection remains challenging due to amplification artifacts, process-mismatch heterogeneity, and limited validation sample sizes. While Bayesian CNV callers naturally quantify per-sample uncertainty, translating this into the frequentist population-level guarantees required for […]
Generating Concept Lexicalizations via Dictionary-Based Cross-Lingual Sense Projection
arXiv:2604.14397v1 Announce Type: cross Abstract: We study the task of automatically expanding WordNet-style lexical resources to new languages through sense generation. We generate senses by associating target-language lemmas with existing lexical concepts via semantic projection. Given a sense-tagged English corpus and its translation, our method projects English synsets onto aligned target-language tokens and assigns the […]
VeriGraphi: A Multi-Agent Framework of Hierarchical RTL Generation for Large Hardware Designs
arXiv:2604.14550v1 Announce Type: cross Abstract: Generating synthesizable Verilog for large, hierarchical hardware designs remains a significant challenge for large language models (LLMs), which struggle to replicate the structured reasoning that human experts employ when translating complex specifications into RTL. When tasked with producing hierarchical Verilog, LLMs frequently lose context across modules, hallucinate interfaces, fabricate inter-module […]
HUOZIIME: An On-Device LLM-enhanced Input Method for Deep Personalization
arXiv:2604.14159v1 Announce Type: cross Abstract: Mobile input method editors (IMEs) are the primary interface for text input, yet they remain constrained to manual typing and struggle to produce personalized text. While lightweight large language models (LLMs) make on-device auxiliary generation feasible, enabling deeply personalized, privacy-preserving, and real-time generative IMEs poses fundamental challenges.To this end, we […]
QU-NLP at ArchEHR-QA 2026: Two-Stage QLoRA Fine-Tuning of Qwen3-4B for Patient-Oriented Clinical Question Answering and Evidence Sentence Alignment
arXiv:2604.14175v1 Announce Type: cross Abstract: We present a unified system addressing both Subtask 3 (answer generation) and Subtask 4 (evidence sentence alignment) of the ArchEHR-QA Shared Task. For Subtask 3, we apply two-stage Quantised Low-Rank Adaptation (QLoRA) to Qwen3-4B loaded in 4-bit NF4 quantisation: first on 30,000 samples from the emrQA-MedSQuAD corpus to establish clinical […]
QualiaNet: An Experience-Before-Inference Network
arXiv:2604.14193v1 Announce Type: cross Abstract: Human 3D vision involves two distinct stages: an Experience Module, where stereo depth is extracted relative to fixation, and an Inference Module, where this experience is interpreted to estimate 3D scene properties. Paradoxically, although our experience of stereo vision does not provide us with distance information, it does affect our […]
PriHA: A RAG-Enhanced LLM Framework for Primary Healthcare Assistant in Hong Kong
arXiv:2604.14215v1 Announce Type: cross Abstract: To address the unsustainable rise in public health expenditures, the Hong Kong SAR Government is shifting its strategic focus to primary healthcare and encouraging citizens to use community resources to self-manage their health. However, official clinical guidelines are fragmented across disparate departments and formats, creating significant access barriers. While general-purpose […]
Magnitude Is All You Need? Rethinking Phase in Quantum Encoding of Complex SAR Data
arXiv:2604.14229v1 Announce Type: cross Abstract: Synthetic Aperture Radar (SAR) data is inherently complex-valued, while quantum machine learning (QML) models naturally operate in complex Hilbert spaces. This apparent alignment suggests that incorporating both magnitude and phase information into quantum encoding should improve performance in SAR Automatic Target Recognition (ATR). In this work, we systematically evaluate this […]