large language models

OmegaGenome: source code

Source code accompanying OmegaGenome: Toward Better Sub-Million Scale Expert Models from Large Genomic Language Models via Knowledge Distillation (Science Advances): teacher fine-tuning, two-stage knowledge distillation, evaluation, the base-resolution multi-track regression pipeline, and the code that produces the pap...

DISSICON: DISSINET lexico-semantic network of concepts and actions

This is a JSON-format, machine-operable, open-licence lexicographic resource, which forms a subset of the research database of the “Dissident Networks Project” (DISSINET, https://dissinet.cz). It focuses on conceptual and verbal entities which hold the database semantically together - its lexico-semantic network. DISSI...

Evaluation of an Artificial Intelligence–Driven Language Model for Age-Specific Patient Education in Pediatric Orthopaedics

GenAI LLMs can generate age-specific explanations for common surgical procedures, treatments, and diagnostic markers in pediatric orthopaedics using an artificial intelligence language model based on the child's age.

Evaluating Harm Reduction Advice From Large Language Models.

A novel method for evaluating LLMs' potential effectiveness for harm reduction across common techniques and situations was presented, and most of the tested LLMs provided reasonable information in a non-judgmental manner, but they also provided misinformation, and some wouldn't answer questions due to built-in safety p...

Large Language Models for simplifying directly-follows graphs in support of self-regulated learning

MAESTRO: Fine-Tuned Multiagent Large Action Model-Based GenAI Assistant Integrating IoT Sensing, Smart Control, and Extended Reality for Human-Building Interaction

The potential of integrating fine-tuned LAM-based agents with structured IoT-enabled middleware and XR-based HBI systems is shown, demonstrating how foundation-model reasoning and actuation can support more intelligent and adaptive HBI workflows.

Retrieval-augmented large language models for automated story point estimation across agile projects

GeoAgentbench: a dynamic execution benchmark for tool-augmented agents in spatial analysis

The integration of Large Language Models (LLMs) into Geographic Information Systems (GIS) marks a paradigm shift toward autonomous spatial analysis. However, evaluating these LLM-based agents remains challenging due to the complex, multi-step nature of geospatial workflows. Existing benchmarks primarily rely on static...

What’s so terrible about being two? The developmental needs of two-year-olds and implications for service provision In Northern Ireland

Early intervention has been a recurrent theme in addressing educational underachievement for children who are at risk of experiencing multiple adversities and undesirable outcomes (Dawson, Dunn and Morgan, 2010). However, there has been some dispute regarding the definition of early intervention - as to whether it shou...

Defusing Logic Bombs in Symbolic Execution with LLM-Generated Ghost Code

Symbolic execution is a powerful program analysis technique, but its effectiveness is fundamentally limited by solver-hostile program fragments, complex numerical reasoning, and unbounded heap structures. Recent work proposed replacing constraint solvers with large language models (LLMs) to bypass these limitations, bu...

Accelerating scientific discovery using domain adaptive language modelling

Research has been conducted for numerous centuries but recent advances in technology have facilitated and accelerated the process keeping the research budget and the required effort at manageable levels. Scientific and technical corpora, such as papers and patents, are great written sources of already existing research...

Interpretable semantic representations from neural language models and computer vision

Recent years have seen a remarkable increase in the computational power we have at our disposal, which has been the driving force behind the emergence of large scale deep learning systems. Today, the field of computational linguistics is dominated by high capacity neural models that in many cases outperform even human...