The Lancet

Beyond artificial intelligence psychosis: a functional typology of large language model-associated psychotic phenomena

A man breached Windsor Castle with a crossbow after his large language model (LLM)-based companion encouraged an assassination plan. A father’s question about pi evolved into more than 300 h of ...
Communications of the ACMOpinion

Communication Bias in Large Language Models: A Regulatory Perspective

Though new regulatory frameworks address fairness, accountability, and safety in AI systems, they often fail to directly ...
The American Journal of Managed Care

Large Language Model Shows Promise for Automating SALT Scoring in Pediatric Alopecia Areata

GPT-4o achieved ICC/CCC of 0.815/0.866 versus in-person SALT scoring and 0.833/0.817 versus image-based scoring, while expert ...
IEEE

Finetuning Large Language Models for Vulnerability Detection

Abstract: This paper presents the results of finetuning large language models (LLMs) for the task of detecting vulnerabilities in Java source code. We leverage WizardCoder, a recent improvement of the ...

RAG vs Long Context for LLMs : When Each Approach Works Best

Choosing RAG or long context depends on dataset size, with RAG suited to dynamic knowledge bases and long context best for bounded files.
IEEE

Covert Prompt Transmission for Secure Large Language Model Services

Abstract: This paper investigates covert prompt transmission for secure and efficient large language model (LLM) services over wireless networks. We formulate a latency minimization problem under ...