large language models

Semantic Privilege Collapse: Trust Boundaries and Execution-Level Authorization in Agentic AI Systems

Large language model agents operating within tool-enabled pipelines create opportunities for untrusted content to influence consequential actions. This note introduces semantic privilege collapse as an architectural failure condition in which task data or insufficiently authorized instructions are promoted into effecti...

What a language model does when you poke it: the clinical map of the Perturbational Complexity Index, pre-registered and reproduced in Pythia-410m

The Perturbational Complexity Index (PCI) decides whether a human is conscious without asking them: a brief transcranial pulse, and the EEG tells whether the response is long and complex (wakefulness) or short and simple (anaesthesia, deep sleep). This record applies the same logic to an open language model that nobody...

Moral masquerade: large language models show a choice-reason dissociation under cross-cultural ethical framing - analysis plan and preregistration

Analysis plan (registered after data collection), preregistration of an ongoing governance experiment, and experimental materials. Anonymous during peer review.

PODCAST: Extracting airline emission KPIs from sustainability reports using large language models (LLMs).

This is a 6 min Podcast of the summary of research paper Martín-Domingo, L., Fernandez, J. B., Efthymiou, M., & Ali, M. I. (2025). Extracting airline emission KPIs from sustainability reports using large language models (LLMs). Transportation Research Interdisciplinary Perspectives, 33, 101599. https://doi.org/10.1016/...

RAG-ReAct empowered large language models for localized intelligent bridge operation and maintenance: a knowledge-driven agentic approach

Bridges serve as critical transportation infrastructure hubs. The recent breakthroughs in large language models (LLMs) offer transformative potential for intelligent bridge operation and maintenance (O&M), but their direct application is hindered by domain-specific hallucination, black-box reasoning opacity, and passiv...

Specification-First Design of a Multi-Agent Short-Form Video Production Pipeline: Typed Stage Contracts, Offline Contract Validation, and an Audit of Evaluation Gaps

Producing short-form vertical video well takes many coordinated roles. This report describes the Agentic Reel Studio (ARS), a specification-first design for a pipeline of large language model (LLM) agents covering that chain, from strategy through editing, sound, motion graphics, and quality control. Each agent owns on...

Large Language Models for Intelligent Data Engineering: Automating Schema Design, Lineage, and Quality Control

This research investigates the application of large language models (LLMs) to automate key data engineering tasks, including schema design, data lineage tracking, and quality control. It presents an integrated framework combining language models with traditional data engineering tools to improve productivity while main...

ULE Framework Scoring Dataset: United States and Türkiye

Version 1 — first deposit The condition-level scoring record for a most-different systems comparison of the legal enablement of ecology-oriented urban living labs in the United States and Türkiye. Five jurisdictions are scored as separate profiles — the United States at federal level, New York City, Portland, Türkiye a...

Enhancing Knowledge Management in Green Building Engineering: A Hybrid Retrieval-Augmented Generation Approach to Support Project Assessment

Green building assessment relies heavily on manual queries of complex engineering regulations, making the introduction of knowledge management theories crucial for improving assessment efficiency. However, the inherent characteristics of engineering regulations—dense terminology, complex clause dependencies, and freq...

Dosezy

v2.5.10: Dosage Units (mEq, Puffs, Ampules), Home Timeline View, Slide Alarm Actions, and Appearance Settings Summary of Changes Release v2.5.10 introduces support for additional medication dosage units (mEq, puffs, and ampules), a clean expanded vertical timeline view for the home screen, dedicated sliding gesture tra...

Chatgpt As The Gatekeeper: Accuracy Of A Large Language Model In Extracting Rnfl Parameters And Detecting Glaucomatous Structural Damage From Oct Reports

System Prompt Governance in Large Language Model Applications: A Systematic Scoping Review and Conceptual Synthesis

Supporting materials for scoping review: Literature list