activity
20242026
collaborators

14 papers

cs.CL2026

Can "AI" Be a Doctor? A Study of Empathy, Readability, and Alignment in Clinical LLMs

Mariano Barone, Francesco Di Serio, Roberto Moio +4

Large Language Models (LLMs) are increasingly deployed in healthcare, yet their communicative alignment with clinical standards remains insufficiently quantified. We conduct a mult…

cs.CV2026

Brain3D: Brain Report Automation via Inflated Vision Transformers in 3D

Mariano Barone, Francesco Di Serio, Giuseppe Riccio +4

Current medical vision-language models (VLMs) process volumetric brain MRI using 2D slice-based approximations, fragmenting the spatial context required for accurate neuroradiologi…

cs.MA2026

From Who They Are to How They Act: Behavioral Traits in Generative Agent-Based Models of Social Media

Valerio La Gatta, Gian Marco Orlando, Marco Perillo +2

Generative Agent-Based Modeling (GABM) leverages Large Language Models to create autonomous agents that simulate human behavior in social media environments, demonstrating potentia…

cs.AI2026

Are LLMs Ready for TOON? Benchmarking Structural Correctness-Sustainability Trade-offs in Novel Structured Output Formats

Elio Masciari, Vincenzo Moscato, Enea Vincenzo Napolitano +3

Large Language Models (LLMs) are increasingly required to generate structured, machine-readable outputs for downstream systems. While recent benchmarks have focused on evaluating t…

cs.CL2025

SOLVE-Med: Specialized Orchestration for Leading Vertical Experts across Medical Specialties

Roberta Di Marino, Giovanni Dioguardi, Antonio Romano +5

Medical question answering systems face deployment challenges including hallucinations, bias, computational demands, privacy concerns, and the need for specialized expertise across…

cs.MA2025

Emergent Coordinated Behaviors in Networked LLM Agents: Modeling the Strategic Dynamics of Information Operations

Gian Marco Orlando, Jinyi Ye, Valerio La Gatta +4

Generative agents are rapidly advancing in sophistication, raising urgent questions about how they might coordinate when deployed in online ecosystems. This is particularly consequ…