large language models

Long-tail knowledge extraction from historical documents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

A GenAI tool was developed that used a Large Language Model capable of answering typical questions for a DMP after receiving the original research proposal as input, and showed a very good capability in providing appropriate responses to most of the DMP questions.

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...

functional-standard-atlas: attenuation-corrected, territory-resolved benchmarking of variant effect predictors against saturation genome editing

functional-standard-atlas: attenuation-corrected, territory-resolved benchmarking of variant effect predictors against saturation genome editing Software and frozen data underlying the manuscript "Measurement reliability bounds functional benchmarks and relocates where variant effect prediction fails" (N. Zhang). WHAT...

Parallel Dialogues: What LLM Inference Can (and Cannot) Teach Us About the Many-Worlds Interpretation — A Companion Note

A companion note to "Evidence for the Many-Worlds Interpretation of Quantum Mechanics via Large Language Model Architecture" (10.5281/zenodo.20533902). Revisits the structural analogy between parallel LLM inference and Everettian branching honestly: identifies what the analogy illustrates well (shared origin, isolated...

Parallel Dialogues: What LLM Inference Can (and Cannot) Teach Us About the Many-Worlds Interpretation — A Companion Note

A companion note to "Evidence for the Many-Worlds Interpretation of Quantum Mechanics via Large Language Model Architecture" (10.5281/zenodo.20533902). Revisits the structural analogy between parallel LLM inference and Everettian branching honestly: identifies what the analogy illustrates well (shared origin, isolated...

Dahono-4B: A Sovereign Foundation Model for Indonesian Legal Reasoning, Statutory Hierarchy Alignment, and Multimodal Document Intelligence

General-purpose Large Language Models (LLMs) predominantly trained on Anglo-American Common Law corpora demonstrate severe jurisdictional fragility when confronted with civil law traditions, frequently exhibiting statutory hallucination, citation of repealed legislation, and systematic disregard for statutory hierarchi...