9 papers
Human Decision-Making with Persuasive and Narrative LLM Explanations
Laura R. Marusich, Mary Grace Kozuch Dhooghe, Jonathan Z. Bakdash +1
Large language models (LLMs) have the potential to aid and improve human decision-making in classification tasks, not only by providing fairly accurate predictions, but also in the…
CASPIAN: Online Detection and Attribution of Cascade Attacks in LLM Multi-Agent Systems via Cross-Channel Causal Monitoring
Kavana Venkatesh, Jafar Isbarov, Saad Amin +2
Cascade attacks in LLM multi-agent systems (MAS) arise when adversarial influence propagates across agents and leads to escalated system-level failures through complex agent intera…
PARALLAX: Separating Genuine Hallucination Detection from Benchmark Construction Artifacts
Khizar Hussain, Murat Kantarcioglu
Large language models (LLMs) hallucinate with confidence: their outputs can be fluent, authoritative, and simply wrong. In medical, legal, and scientific applications this failure…
CourtGuard: A Model-Agnostic Framework for Zero-Shot Policy Adaptation in LLM Safety
Umid Suleymanov, Rufiz Bayramov, Suad Gafarli +4
Current safety mechanisms for Large Language Models (LLMs) rely heavily on static, fine-tuned classifiers that suffer from adaptation rigidity, the inability to enforce new governa…
Ask ChatGPT: Caveats and Mitigations for Individual Users of AI Chatbots
Chengen Wang, Murat Kantarcioglu
As ChatGPT and other Large Language Model (LLM)-based AI chatbots become increasingly integrated into individuals' daily lives, important research questions arise. What concerns an…
Graph Generative Models Evaluation with Masked Autoencoder
Chengen Wang, Murat Kantarcioglu
In recent years, numerous graph generative models (GGMs) have been proposed. However, evaluating these models remains a considerable challenge, primarily due to the difficulty in e…