large language models

Chronometric Injection: A Residual-Stream Channel for Elapsed-Time Conditioning in Frozen Language Models

Large language models can reason about time when temporal information is written in a prompt, but the standard transformer interface provides no first-class input for elapsed wall-clock duration. This limitation matters for interactive and agentic systems, where the same visible prompt may require different responses d...

Auditable AI-Assisted Scientific Discovery: From Noncausal Processes to Quantum Measurement Rigidity

Large language models can accelerate scientific exploration, but generated arguments are not evidence. We report a human–AI research workflow in which model outputs are treated as conjectures and claims are admitted only after proof or deterministic, independently checked computation. The workflow is illustrated by a c...

Algerian Darja Corpus: A 34-Million-Word Long-Form Conversational Dataset for Dialectal Language Modeling

The Algerian Darja Corpus is an open-source, large-scale dataset comprising 11,151 curated long-form conversational transcripts totaling 34,336,366 words (186,106,376 characters, ~53M subword tokens). Key updates in this version:- Added 1,408 newly curated dialogue transcripts from recent media and tech channels.- Re-a...

The Hidden Domestication of Probabilistic Fitting: The Individualization Fallacy and Extended‑Mark Cognitive Architecture

This preprint introduces the individualization fallacy, an original cognitive risk concept for generative large‑language models. Large models produce group‑averaged value narratives from massive corpora and mechanically apply statistical group conclusions onto unique individual real‑world situations. Ordinary cloud‑end...

NHOS Oracle Matrix Search Engine™ A Local Hybrid Retrieval and Contextual Discovery Architecture for Personal Health Knowledge

NHOS Oracle Matrix Search Engine™: A Local Hybrid Retrieval and Contextual Discovery Architecture for Personal Health Knowledge Technical Research White Paper — Version 1.2 · September 2026Corresponding Software Version: NHOS Oracle Matrix Search Engine v8.0.0Research Stage: Implemented Research System & Validation Fra...

Capability-Oriented Software Engineering (COSE): An Incremental Methodology for Building Reusable Capability Libraries

Software engineering projects frequently suffer from architectural re-invention, encapsulating functional knowledge within individual project silos. This paper presents Capability-Oriented Software Engineering (COSE), a formal incremental methodology designed to systematically convert software engineering effort into a...

The Data of Six Large Language Models on Four Core Medical School Courses

Large language models (LLMs) have demonstrated remarkable potential in medical education, yet their performance on discipline-specific medical school course examinations remains incompletely characterized. This study evaluated six contemporary LLMs on final examinations for four core medical school courses: Surgery, Mu...

Cost-Amortised Reasoning via Self-Distilling Neuro-Symbolic Cascades: From Knowledge-Graph QA to Regulatory-Compliance Checking

Large language models make knowledge-graph question answering (KGQA) fluent, but every query pays the full price of an LLM call. We present TACET (Latin: it is silent), a self-distilling neuro-symbolic cascade that amortises that cost by progressively migrating a streamed workload off the LLM and onto cheap, checkable...

Multilingual Sentiment-Aware Text Summarization: A Reinforcement Learning Approach for Consistency Maintenance

Reproducibility Artifacts for an Integrated Blockchain and Large Language Model Decision Support System for Organ Donation and Transplantation Workflows

This release adds reproducibility support for the revised evaluation: separates strict output completion, classification performance conditional on valid output, and failure-penalized end-to-end performance; adds a 20-scenario post hoc robustness suite covering safeguard boundary conditions, invalid model outputs, and...

spec-resistance corpus: 30-model, 627,491-trial dataset for "Large language models that near-perfectly evaluate products systematically recommend a worse familiar brand"

Primary computational corpus for the manuscript "Large language models that near-perfectly evaluate products systematically recommend a worse familiar brand" (Affonso, Spears School of Business, Oklahoma State University). Contains 627,491 controlled product-recommendation trials across 30 frontier language models from...

The Core Ring: Composition, Not Components, Is What Large Language Models Lack

Large language models have improved chiefly by scaling one monolithic computation. We argue the binding constraint is no longer missing components—language, reasoning, and knowledge are all present—but a missing composition in which they form a closed loop. We propose the Core Ring, an architecture with no single core....