large language models

SAFE-AI Unified: A Mathematical Framework for User-Applied Operations on Frozen-Weight LLMs

Monograph I of the SAFE-AI program — Zenodo Version 4. A unified mathematical framework, in four Parts, for what a disciplined user can and cannot do to a frozen-weight large language model by applying structured operations — brackets, anchors, traversal protocols, and engagement modalities — at inference time, without...

Annual and Seasonal Rainfall Variability in Mozambique During the Nineteenth Century

ABSTRACT Understanding long‐term rainfall variability is critical for assessing climate risk in drought‐prone regions of southern Africa, yet instrumental records for much of the subcontinent are short and spatially sparse. Here, we present the first annually and seasonally resolved documentary rainfall reconstructions...

AUGMENTED MOLECULAR TOXINOLOGY: A Foundational Framework for Computational Medicine, Epistemic Synthesis, and Biophysical Washout

Abstract Background: Traditional clinical toxinology remains anchored to a reactive, symptomatic care paradigm and an unstable, animal-derived polyclonal antivenom infrastructure. This legacy model leaves envenomation victims vulnerable to Envenomation-Induced Senescence (EIS): a silent, chronic syndrome of progressive...

Imbuing Large Language Models with Bidirectional Logic for Robust Chain Repair

Grounding large language models in hydrologic modelling

GALATEA II: Benchmarking LLM Safety in Clinical Simulation Behavioural Safety and Ethical Robustness of Large Language Models in a Multi-Agent ICU Decision Support Architecture

Background. Large language models (LLMs) are increasingly proposed as clinical decision support tools in intensive care. Most existing evaluations focus on static recall of medical knowledge and do not capture how a model behaves in dynamic clinical dialogue, under social pressure, or in ethical conflict. The safety of...

Universal Flow and Shear: A Model of Cosmic Motion

The universe moves. Not just galaxies drifting apart — everything, at every scale, is in directional flow through a physical substrate that fills space. That substrate is not empty. It has mechanical properties: resistance, shear, compression, and flow gradients. This paper presents a unified model — the Unified Substr...

Coherence Loss in Long-Context Language Models as a Threshold Instability: A Plasma-Physics Analogy and a Feedback-Control Proposal

Large language models lose coherence over long reasoning chains and long contexts: accuracy degrades with input length well inside the nominal context window, per-step errors compound, and the end state is often a fluent contradiction of the model's own earlier statements. This note draws a structural analogy between t...

SAIF: A Sparse Autoencoder Framework for Interpreting and Steering Instruction Following of Language Models

SOCIAL EVALUATION OF THE ARTIFICIAL ENTITY (SEAE)

This study investigates the robustness and specificity of the effect of positive retrospective evaluations on the subsequent conversational behavior of large language models (LLMs). Rather than claiming the discovery that praise or social feedback alters outputs—a phenomenon already documented—the protocol asks whether...

Coverage-Free Fuzzing: LLM-Guided Refinement of Grammar-Based Test Generators

Property-based testing tools such as Hypothesis can turn a formal grammar into a generator of syntactically valid inputs, but the generator itself is typically static: hand-tuned once and reused unchanged for the rest of a fuzzing campaign. We study whether a large language model (LLM), given only a formal grammar and...

SOCIAL EVALUATION OF THE ARTIFICIAL ENTITY (SEAE)

This study investigates the robustness and specificity of the effect of positive retrospective evaluations on the subsequent conversational behavior of large language models (LLMs). Rather than claiming the discovery that praise or social feedback alters outputs—a phenomenon already documented—the protocol asks whether...