large language models

Structure Before Content: Why Probabilistic AI Requires Prior Structural Commitment

Large language models are commonly evaluated by the quality of the content they generate. This paper argues that this focus is fundamentally misplaced. In probabilistic systems, content quality is a secondary property; the primary determinant of meaning, reliability, and trustworthiness is the existence of explicit pri...

Dataset and Analysis Scripts for: An 8-Week LLM Speaking Intervention and EFL Anxiety: A Mixed-Methods Pilot

This dataset accompanies a mixed-methods pilot study of an eight-week intervention (22 October – 17 December 2025). In the intervention, 54 university EFL students in China used freely available large language model chatbots for low-stakes speaking practice. The chatbots used were DeepSeek, Doubao, ChatGPT, Kimi Chat a...

Atmospheric Multiscale Operational Foundation in USP Field Theory

msf:47220 v2.0 establishes the atmospheric master foundation of USP Field Theory. The document begins from standard atmospheric physics rather than from a USP-specific force or frequency law. Its operational hierarchy is: standard dynamical closure → forcing and boundary conditions → transport and phase change → organi...

Project Brahmaand: Sovereign, Non-Autoregressive Edge Intelligence via 24-Dimensional Topological Cartridges, Zero-Multiplication Subtractive Meshes, and Predictive B-Frames

State-of-the-art Large Language Models (LLMs) rely heavily on autoregressive transformer decoders requiring billions of dense floating-point Multiply-Accumulate (MAC) operations, massive memory bandwidth, and centralized cloud server infrastructure. In this paper, we introduce Project Brahmaand, an edge-native, non-aut...

An Agency-Specific Project Authoring Advisor: LLM-Based RAG System with Automatic Prompt Optimization Method

Abstract Despite the vast potential of large language models (LLMs) in specialized fields, their application in architecture, engineering, and construction (AEC) has been hindered by several challenges, including inaccurate information retrieval, limited access to domain information, inadequate customization of prompts...

Project Brahmaand: Sovereign, Non-Autoregressive Edge Intelligence via 24-Dimensional Topological Cartridges, Zero-Multiplication Subtractive Meshes, and Predictive B-Frames

State-of-the-art Large Language Models (LLMs) rely heavily on autoregressive transformer decoders requiring billions of dense floating-point Multiply-Accumulate (MAC) operations, massive memory bandwidth, and centralized cloud server infrastructure. In this paper, we introduce Project Brahmaand, an edge-native, non-aut...

Watermarking large language models in Europe: interpreting the AI act in light of technology

Abstract To foster trustworthy Artificial Intelligence (AI) within the European Union, the AI Act requires providers to mark and detect the outputs of their general-purpose models. The Article 50 and Recital 133 call for marking methods that are "sufficiently reliable, interoperable, effective and robust". Yet, the rap...

Algorithmic Shortlisting in Participatory Budgeting

This work designs and test privacy-preserving methods for algorithmic shortlisting and proposes a vote-based pipeline that enables state-of-the-art LLMs to perform on par with classical machine learning.

Linguistic Triggers of Gender and Racial Bias in Open-Weight LLMs Applied to Recruitment

Open-weight large language models are rapidly entering hiring pipelines, yet their discriminatory failure modes -- and the regulatory exposure these create under the EU AI Act high-risk classification (Annex III) and U.S. EEOC adverse-impact analysis -- remain poorly understood. We present the first systematic, multi-m...

From a River in Gilead to the Inference Distributions of Large Language Models: Covert Dialect Bias and Linguistic Profiling at Scale

Large language models (LLMs) are increasingly deployed in high-stakes domains such as housing screening. While alignment techniques mitigate explicit racial bias in generated text, they often leave covert attitudinal associations in internal probability distributions untouched. Adapting the matched-guise sociolinguisti...

A multi-site benchmarking framework for scalable extraction of geriatric care constructs from electronic health records

Findings highlight key trade-offs among symbolic, generative, and instruction-tuned approaches for CGA and 4Ms phenotyping, suggesting that hybrid heuristic-LLM methods offer interpretability and stability, whereas large language models provide greater adaptability for complex clinical narratives.

Generative AI And Large Language Models in Intelligent Systems