large language models

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...

A Concern-Centric Empirical Evaluation of Multi-Language Code Smells: An LLM-Assisted Study of JNI Software Evolution

ローカル LLM を用いた数学学習支援アプリの設計と実装

近年,AIを学習の補助に用いる学生が増えている.しかし,無料プランと有料プランでは利用できるモデルや機能に差があり,費用の負担が学習機会の格差につながる可能性がある.そこで私たちは,有料のAIサービスを継続して利用することが難しい生徒にもAIを用いた学習環境を届けるため,数学学習支援アプリを開発した.このアプリは,大規模言語モデル(la...

A Semantic-Enhanced Multi-Task Framework with Structure-Aware Curriculum Learning for Low-Resource Neural Machine Translation

ローカル LLM を用いた数学学習支援アプリの設計と実装

近年,AIを学習の補助に用いる学生が増えている.しかし,無料プランと有料プランでは利用できるモデルや機能に差があり,費用の負担が学習機会の格差につながる可能性がある.そこで私たちは,有料のAIサービスを継続して利用することが難しい生徒にもAIを用いた学習環境を届けるため,数学学習支援アプリを開発した.このアプリは,大規模言語モデル(la...

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...