large language models

Interpretable multimodal retrieval augmented diagnosis for breast ultrasound with multinational clinical validation and reader study

Breast ultrasound is central to breast cancer diagnosis but suffers from substantial inter-observer variability in Breast Imaging Reporting and Data System (BI-RADS) assessment, and existing deep learning models remain opaque. Multimodal large language models promise interpretable report-based reasoning, yet scarce pai...

Pegi1727/Decolonizing-the-Algorithm-DAR-AI-Assisted-L2-Academic-Writing: Decolonizing the Algorithm (DAR) in AI-Assisted L2 Academic Writing: Epistemic Agency, Authorial Voice, and Pre–Post Research Data

Decolonizing the Algorithm (DAR) in AI-Assisted L2 Academic Writing: Epistemic Agency, Authorial Voice, and Pre–Post Research Data Description This research project investigates the Decolonizing the Algorithm (DAR) framework, a critical pedagogical approach designed to support negotiated epistemic agency and authorial...

ISNAD: benchmark data and analysis code for "Accuracy is not reliability" (Information Processing & Management, 2026)

Companion archive for the article Accuracy is not reliability: abstention-aware evaluation of large language models on bio-bibliographic claim verification in classical Islamic scholarship (Information Processing & Management, Elsevier, 2026, in press). Contents: the ISNAD benchmark (1,986 scored Turkish claims across...

Title: A Comprehensive Analysis of Systematic Errors in Large Language Models (LLMs): Evaluating Performance in Complex Economic and Quantitative Reasoning

The Future of Agricultural Extension and Economics: Integrating Artificial Intelligence, Behavioural Science, Climate Resilience and Inclusive Markets

Agricultural extension is being reshaped by four simultaneous pressures: the arrival of low-cost digital and artificial-intelligence-based advisory tools, the reframing of farmer decision-making by behavioural economics, the intensification of climate risk and the restructuring of agri-food markets. These developments...

Same Prompt, Not the Same Instrument: A Preregistered Test of Persona Framing and Moral Concern in Four Large Language Models

Cross-model comparisons of moral judgement assume a shared prompt is a shared instrument. We report a preregistered test of Motivated Violation Construction (MVC), on which a loaded actor identity can move ambiguous behaviour into violation, in Claude Opus 4.7, GPT-5.5, Gemini 3.1 Pro, and DeepSeek-V4-Flash, which clas...

The Particle Accelerator Principle in AI Research Forensics

The Particle Accelerator Principle transitions generative-AI-assisted scientific research from passive textual acceptance to an active, rigorous experimental discipline. A Large Language Model is not an oracle, but a complex, non-linear experimental apparatus.By treating individual AI runs as candidate collision events...

SPReAD採択課題 課題名コーディング 公開データパッケージ / Title classification of SPReAD-funded projects: a reproducibility data package

本データセットは、文部科学省「AI for Science 萌芽的挑戦研究創出事業(SPReAD)」第1回・第2回で採択された課題(計1,112件)の課題名を内容分類した事例研究について、再現に必要な資料一式を収録したものである。 収録物は次の4点である。(1)公式の採択課題一覧PDFから課題レベルの構造化データを作成するパーサ、(2)大規模言語モデル(LLM)によ...

Grounded Reasoning: Autonomous AI for resilient, low-SWaP-C satellite ground infrastructure

The ground segment is often the most accessible and operationally exposed part of a satellite system,yet its automation remains largely rule-based. As satellite constellations multiply, ground infrastructure isfragmenting into many small, remote and often contested sites, yet each still depends on either a link backto...

CHSH-Form Values Above 2 for Standard Fibonacci Anyons, and the Non-Topological Origin of Finite-Size Sector–CHSH Mutual Information in Z2 Lattice Gauge Theory

We quantify the mutual information I between topological sector labels T and CHSH values S in two-dimensional lattice models. Throughout, I denotes a classical Shannon mutual information between a global discrete label and a scalar measured value; it is not an entanglement entropy between spatial regions. In the Z₂ lat...

LLMs Simulate the Description of a Culture, Not the Culture: An Attempt to Reproduce Henrich's Cross-Cultural Ultimatum Game Finding with LLM Agents

Describing a cultural identity to a large language model (LLM) and using it in place of human participants is increasingly common in generative agent-based modeling. We test this method against a well-documented cross-cultural finding: in the Ultimatum Game, WEIRD students often reject low offers, while members of smal...

The AI System of Record: Governance for Agentic AI

Agentic AI is being increasingly implemented in organizations and is becoming more autonomous. However, enterprise data remains fragmented, inconsistent, and potentially stale, while large language models (LLMs) are not completely deterministic. Moreover, governance, control, and traceability are often lacking when AI...