arXiv:2603.18101v1 Announce Type: cross Abstract: Recent adapter-based CLIP tuning (e.g., Tip-Adapter) is a strong few-shot learner, achieving efficiency by caching support features for fast prototype matching. However, these methods rely on global uni-modal feature vectors, overlooking fine-grained patch relations and their structural alignment with class text. To bridge this gap without incurring inference costs, we […]
The Validity Gap in Health AI Evaluation: A Cross-Sectional Analysis of Benchmark Composition
arXiv:2603.18294v1 Announce Type: new Abstract: Background: Clinical trials rely on transparent inclusion criteria to ensure generalizability. In contrast, benchmarks validating health-related large language models (LLMs) rarely characterize the “patient” or “query” populations they contain. Without defined composition, aggregate performance metrics may misrepresent model readiness for clinical use. Methods: We analyzed 18,707 consumer health queries across […]
VC-Soup: Value-Consistency Guided Multi-Value Alignment for Large Language Models
arXiv:2603.18113v1 Announce Type: cross Abstract: As large language models (LLMs) increasingly shape content generation, interaction, and decision-making across the Web, aligning them with human values has become a central objective in trustworthy AI. This challenge becomes even more pronounced when aligning multiple, potentially conflicting human values. Although recent approaches, such as reward reweighting, prompt-based supervised […]
MedMASLab: A Unified Orchestration Framework for Benchmarking Multimodal Medical Multi-Agent Systems
arXiv:2603.09909v2 Announce Type: replace Abstract: While Multi-Agent Systems (MAS) show potential for complex clinical decision support, the field remains hindered by architectural fragmentation and the lack of standardized multimodal integration. Current medical MAS research suffers from non-uniform data ingestion pipelines, inconsistent visual-reasoning evaluation, and a lack of cross-specialty benchmarking. To address these challenges, we present […]
Understanding Task Aggregation for Generalizable Ultrasound Foundation Models
arXiv:2603.18123v1 Announce Type: cross Abstract: Foundation models promise to unify multiple clinical tasks within a single framework, but recent ultrasound studies report that unified models can underperform task-specific baselines. We hypothesize that this degradation arises not from model capacity limitations, but from task aggregation strategies that ignore interactions between task heterogeneity and available training data […]
Consumer-to-Clinical Language Shifts in Ambient AI Draft Notes and Clinician-Finalized Documentation: A Multi-level Analysis
arXiv:2603.18327v1 Announce Type: new Abstract: Ambient AI generates draft clinical notes from patient-clinician conversations, often using lay or consumer-oriented phrasing to support patient understanding instead of standardized clinical terminology. How clinicians revise these drafts for professional documentation conventions remains unclear. We quantified clinician editing for consumer-to- clinical normalization using a dictionary-confirmed transformation framework. We analyzed […]
Retrieval-Augmented LLMs for Security Incident Analysis
arXiv:2603.18196v1 Announce Type: cross Abstract: Investigating cybersecurity incidents requires collecting and analyzing evidence from multiple log sources, including intrusion detection alerts, network traffic records, and authentication events. This process is labor-intensive: analysts must sift through large volumes of data to identify relevant indicators and piece together what happened. We present a RAG-based system that performs […]
Biased AI can Influence Political Decision-Making
arXiv:2410.06415v4 Announce Type: replace-cross Abstract: As modern large language models (LLMs) become integral to everyday tasks, concerns about their inherent biases and their potential impact on human decision-making have emerged. While bias in models are well-documented, less is known about how these biases influence human decisions. This paper presents two interactive experiments investigating the effects […]
Discovering What You Can Control: Interventional Boundary Discovery for Reinforcement Learning
arXiv:2603.18257v1 Announce Type: cross Abstract: Selecting relevant state dimensions in the presence of confounded distractors is a causal identification problem: observational statistics alone cannot reliably distinguish dimensions that correlate with actions from those that actions cause. We formalize this as discovering the agent’s Causal Sphere of Influence and propose Interventional Boundary Discovery IBD, which applies […]
FaithSteer-BENCH: A Deployment-Aligned Stress-Testing Benchmark for Inference-Time Steering
arXiv:2603.18329v1 Announce Type: new Abstract: Inference-time steering is widely regarded as a lightweight and parameter-free mechanism for controlling large language model (LLM) behavior, and prior work has often suggested that simple activation-level interventions can reliably induce targeted behavioral changes. However, such conclusions are typically drawn under relatively relaxed evaluation settings that overlook deployment constraints, capability […]
Quantifying Student Success with Generative AI: A Monte Carlo Simulation Informed by Systematic Review
arXiv:2507.01062v3 Announce Type: replace-cross Abstract: The rapid development of generative artificial intelligence (GenAI) tools such as ChatGPT has intensified interest in their role in higher education, particularly in how students perceive and use them and how these perceptions may relate to educational outcomes. This study employs a hybrid methodological approach that combines a PRISMA-guided systematic […]
MemArchitect: A Policy Driven Memory Governance Layer
arXiv:2603.18330v1 Announce Type: new Abstract: Persistent Large Language Model (LLM) agents expose a critical governance gap in memory management. Standard Retrieval-Augmented Generation (RAG) frameworks treat memory as passive storage, lacking mechanisms to resolve contradictions, enforce privacy, or prevent outdated information (“zombie memories”) from contaminating the context window. We introduce MemArchitect, a governance layer that decouples […]