large language models

Measuring Curriculum Alignment across Topical Coverage, Competency, and Cognitive Depth: A Cross-Generational Framework Applied to CS2013 and CS2023

This archive contains the data, alignment maps, rater materials, and source code needed to audit and reproduce every figure and table in the manuscript. The study measures how completely an accredited BSc Computer Science program covers the ACM/IEEE/AAAI computing body of knowledge through three nested lenses: topical...

Mechanistic control of large language models as simulated participants via linear representation

Spatiotemporal dynamics of lexical and morphosyntactic planning during language production revealed by magnetoencephalography

Fluent sentence production relies on the precise and timely coordination of lexical retrieval, morphosyntactic planning, and motor execution. While a left-dominant fronto-parieto-temporal network has been identified for these subcomponents of sentence production, less is known about the time course of engagement of the...

An Improved Prediction Method for Telemetry Time Series Based on a Large Language Model

Is there a way to improve language models accuracy in solving physics problems in Russian and English languages?

Large language models are increasingly used to solve educational physics problems, but their accuracy remains inconsistent. This study investigates whether prompt formulation can improve the performance of language models on school-level physics problems in Russian and English. In total 21 language models were tested o...

Genre-Routed Generative Resonance: Black-Box AI Text Detection via Dual-Horizon Probing and Structural Rhythm

Detecting text synthesized by frontier large language models (LLMs) remains a critical requirement for academic integrity, digital forensics, and media authenticity. Existing zero-shot detectors exhibit severe real-world failure modes: token-curvature methods (DetectGPT, Fast-DetectGPT) require inaccessible white-box m...

Zero-Copy In-Place Compaction and Idempotent Associative Routing of Dynamic Key-Value Cache Tensors in Deep Learning Accelerators

The serving of autoregressive Large Language Models (LLMs) is severely constrained by the computational and memory capacity limits of the Key-Value (KV) cache, commonly referred to as the Memory Wall. While dynamic context pruning algorithms mitigate memory expansion by discarding tokens of low attention mass, conventi...

Scaffolding students-AI dialogue for safe educational interactions

The Steered Contextual AI Framework for Orchestrating Learning Dialogue (SCAFFOLD), a layered reliability architecture that surrounds LLM-generated text and speech with external verification, targeted repair, and safe fallback, while preserving data privacy, is proposed.

Between Methodological Expansion and Epistemic Boundary Dissolution: Generative AI, Distributed Epistemic Processes, and the Reorganization of Scientific Responsibility

Although individual studies have examined the capabilities of generative AI in annotation, coding, item construction, thematic analysis, and data simulation, there has so far been no cross-paradigm framework that systematically integrates technical performance, methodological validity, institutional embedding, and the...

Autonomous Agents as First-Class Operating System Entities: Formal Architecture, Deterministic Protocols, and Self-Regulating Runtimes

Modern multi-agent architectures predominantly treat autonomous agents driven by Large Language Models (LLMs) as unmanaged application-level loops interacting through stateless, unbounded prompts. In long-running computing environments, this abstraction mismatch induces severe system-level pathologies, including nondet...

A Few-shot Learning Approach for Dynamic Arabic Sign Language Recognition

Sign language's importance comes from its vital role in improving the lifestyle of deaf and hearing-impaired people.Despite the importance of Arabic Sign Language (ArSL) in playing this vital role in the Arab world, ArSL recognition researches are still limited.This limitation is largely due to the lack of high-quality...

Retrieval-Augmented Large Language Models for Real-Time Supply Chain Disruption Intelligence and Decision Support

Large language models offer unprecedented analytical capability, but their knowledge is frozen at the last training date — rendering them unusable for organizations whose mission depends on emerging, timely information [1]. This paper argues that retrieval-augmented generation is the missing mechanism that converts LLM...