small language model

Utilization of a HIPAA-compliant large language model chatbot in an academic pediatric medical center

Despite growing interest in LLM chatbots, little evidence exists on usage patterns in hospital systems. This paper presents a mixed-methods case study of “InternalGPT,” a HIPAA-compliant LLM chatbot made available to employees of the institution. Survey responses and 14 months of system utilization data were analyzed a...

A trainable language model with potential to modulate translation rates in non-model organisms by generating upstream untranslated region sequence libraries

A simple generative approach for creating synthetic 5′-UTR libraries based solely on the genomic sequence statistics of any desired organism and demonstrates that simple statistical language model approaches applied to genomic data can generate functional translational regulatory sequence libraries without detailed mec...

A Multilingual Media Analysis of Pediatric and Thyroid-Related Newspaper Communications Following the Chernobyl and Fukushima Nuclear Disasters

Public media communication, particularly through newspapers, plays a critical role in shaping public awareness, governmental response, and remediation efforts following large-scale crises, including nuclear power plant accidents. Because children are biologically more vulnerable to the effects of ionizing radiation, un...

Investigating the Comprehensibility Paradigm: Key Fluency Predictors in L1 English Speakers' Evaluations of Japanese Speakers' L2 English.

The present study investigates the relationship between first language (L1) and second language (L2) oral fluency and their association with comprehensibility in lower-intermediate Japanese learners of English, examining which L2 fluency features are most closely associated with L1 English listeners' comprehensibility...

Large Language Model-Based Text-to-Cypher Generation for Question-Answering on Biomedical Knowledge Graphs.

Few-shot prompting heavily improves query generation quality and enables effective use of smaller models, supporting the practical deployment of locally hosted LLMs for knowledge graph question answering.

Small Language Models for Early Alzheimer’s Risk Detection: Accuracy-Efficiency Trade-Offs in the DMV Framework

Root, Suffix, or Byte? A Reproducible Study of Sub Word Tokenization for a Morphologically Rich Language (Russian)

Tokenization is the first design choice in a language model and one of the most frequently overlooked for morphologically rich languages, as it directly shapes sequence length and how related word forms are segmented into reusable sub word units. Using Russian as a case study, we train sub word tokenizers from scratch...

DEVELOPMENT OF AN INTERACTIVE MATHEMATICS MODULE BASED ON PROBLEM-BASED LEARNING AND ISLAMIC VALUES

A preliminary analysis at SMA Muhammadiyah Al Amin Sorong identified limited use of interactive learning media, low student engagement, and insufficient integration of Islamic values in mathematics learning. Therefore, this study aimed to develop an interactive digital mathematics module based on Problem-Based Learning...

The effect of a Dutch early language intervention on children's oral language skills: a cluster randomized controlled trial.

BACKGROUND Early oral language skills are crucial for children's later academic and social development, yet systematic support for oral language development remains limited in Dutch primary education. The Nuffield Early Language Intervention (NELI) has proven effective in improving oral language skills among preschool...

Music Production Communication Overlay (MPCO)

The Music Production Communication Overlay (MPCO) is an evidence-based instructional framework that embeds communication development directly into existing music production coursework by integrating targeted prompts, modeling, and evaluative language into assignments, studio workflows, and feedback cycles. Designed for...

Uncoded Clinical Features from Multilingual Electronic Health Records in Catalonia: Development and Validation Study (Preprint)

BACKGROUND Unstructured free‑text narratives in electronic health records (EHRs) contain critical clinical information that is not captured by structured standard codes. In Catalonia, primary care notes follow a semi‑structured format known as MEAP (in Catalan). However, extracting structured variables using cloud‑host...

M3: Conversational LLMs simplify secure clinical data access, understanding, and analysis

Large-scale clinical databases offer opportunities for medical research, but their complexity creates barriers to effective use. The Medical Information Mart for Intensive Care (MIMIC-IV), one of the world’s largest open-source electronic health record databases, traditionally requires both SQL proficiency and clinical...