large language models

Clinical AI and Precision Medicine: Philosophical Questions About Labels, Disease, and Evidence

Precision medicine is often framed as a move from “average-patient” care toward prevention, diagnosis, and treatment tailored to individual variability. This aspiration has been articulated in major policy and scientific calls for a new evidence-generating health system and a new taxonomy of disease [ 1 , 2 ]. Yet, the...

Comparing Neighbour Retrieval and Interlinkage Graphs for Sustainable Development Goal Classification with Large Language Models: code, evaluation splits and SDG interaction matrices

Code and artefacts for the Scientific Reports submission. Contains the four analysis notebooks; the reconstructed goal-level SDG interaction matrix and the two text-derived target-level matrices; raw LLM probability arrays for four backbones; the evaluation splits with DOI lists, manifests and labels at goal and target...

From Topology to Troubleshooting: Evaluating Multimodal Large Language Models on Network Management

Large Language Models (LLMs) have been widely applied in various areas due to their comprehension and reasoning capabilities. Although recent research has explored to utilize LLMs in networking areas, the applications in real network environments are still in the early stage due to models’ limitations and inaccurate ou...

Concordance and influence of large language model treatment recommendations versus hematologist decision-making in relapsed/refractory diffuse large B-Cell lymphoma: the Ariadne's thread study

Large language models (LLMs) achieve high scores on medical benchmarks, yet their clinical reasoning capabilities in complex, real-world scenarios remain poorly characterized. This thesis evaluates LLM performance in treatment selection for relapsed/refractory diffuse large B-cell lymphoma (R/R DLBCL), a scenario requi...

Long-tail knowledge extraction from historical documents

Knowledge Extraction (KE) transforms unstructured text into machine-readable representations, enabling automatic Knowledge Graph (KG) generation. Modern KE systems use Large Language Models (LLMs) as core components, leveraging knowledge stored in their parameters through pre-training. LLMs struggle with long-tail know...

Disentangling Threads: Exploring the Potential of LLM-Supported Discussion Forum Analysis for Community Insight

This work manually analyzed a forum discussion, synthesized an exploratory analysis framework from relevant literature, built a design probe, and interviewed 21 researchers to uncover perceived opportunities and barriers with LLM representations of collective discussions.

The AI BATTLE: Evaluating All-Rounder Capabilities in Large Language Models

From curiosity about AI models and with a view to know which AI model is the best all-rounder among the world-leading robust AI models, at first the top 9 of the most popular AI models have been taken to compare. The comparison is based on 4 major requirements: Matching the tool to the workflow (For deep research and a...

KurdishMCQ: A multiple-choice question dataset for the Kurdish language (Sorani dialect)

KurdishMCQ is, to the authors' knowledge, the first large-scale, publicly available collection of multiple-choice questions in the Kurdish language (Sorani dialect), supporting the evaluation of large language models in low-resource settings. Version 2 contains 17,221 questions digitized from Kurdish school textbooks,...

A Recurrence Converse for Identity Persistence: The Verdict Channel and the Storage–Persistence Capacity Gap

Abstract This paper characterizes recurrence and distinguishable-history capacity in finite declared identity regimes. For the class-indexed observable, the central quantity is the logarithm of the spectral radius of the reachable recurrent subgraph. A recurrence converse bounds sound retention codes by this capacity,...

GenAI for Research Support: A Case to DMPs Pre-Filling

  Our aim with this report was to present the application of Generative AI (GenAI) in the preparation of Data Management Plans (DMPs), which are typically mandatory for funded research proposals. We developed a GenAI tool that used a Large Language Model (LLM) capable of answering typical questions for a DMP (e.g., Wha...

Fine-Tuning Pre-trained Vision-Language Models in a Human-Annotation-Free Manner

Semantic Phase Theory: An Information-Theoretic Framework for Meaning and Context

This paper introduces Noetica Theory, a meaning-phase model in which semantic entities are represented as wave functions defined over context-dependent phase spaces. We define raw and normalized meaning wave functions, noetica energy, semantic entropy, semantic free energy, and semantic interference, and we formulate a...