large language models

Evaluating and Mitigating Hallucinations in Retrieval-Augmented Question Answering over Uzbek School Textbooks

Large language models for patient-centred evidence generation and use

Preprint. Not peer reviewed. For people with multimorbidity, disease-specific evidence can leave practical questions unanswered. We propose an evidence operating system (Evidence OS) that follows patient priorities through evidence synthesis, research and the return of findings to care. Large language models could assi...

Large language models for patient-centred evidence generation and use

Preprint. Not peer reviewed. For people with multimorbidity, disease-specific evidence can leave practical questions unanswered. We propose an evidence operating system (Evidence OS) that follows patient priorities through evidence synthesis, research and the return of findings to care. Large language models could assi...

EasyScan_HEP 2: LLM-agent parameter-scan workflows in high energy physics

Abstract Large-language-model (LLM) agents are beginning to reshape the preparation and steering of computational workflows in high-energy physics phenomenology. To accommodate this change, we upgrade _ to make the construction of parameter-scan configuration files more accessible to LLM-agent assistance. _ exposes com...

Research Gap Discovery Dataset: LLM-Extracted Limitations and Research Gaps from 3,326 Scientific Papers

This dataset contains 3,326 recent arXiv computer science papers (first versions dated 16 March to 17 July 2026). For each paper, a large language model read the title and abstract and wrote one sentence each on the paper's main limitation, an open research gap for future work, and why that gap matters. It was built to...

Frontier AI as Strategic Infrastructure: Sovereign Governability Under Dependency

When personal data enters an artificial-intelligence development lifecycle, deleting the original record may not end the consequences of an unlawful, deceptive, or otherwise prohibited data practice. The data may have informed a model, algorithm, embedding, feature set, evaluation corpus, or other operational artifact....

Resolving the Full Modular Data of a Doubled-Fibonacci String-Net on a Finite Torus by Point-Group Rotation, and an Obstruction to Quasi-One-Dimensional Anyon Exchange

We report a real-space resolution of the full modular data of a doubled-Fibonacci Levin–Wen string-net, obtained by exact diagonalization on finite torus supercells (2×2, 2×3, 3×3), together with a sharply scoped negative result for the dynamical half of the same program — and we keep the classes of evidence strictly s...

Decision Without Generation: Benchmarking a Calibrated Non-Generative Decision Model Against LLM Judges on Moderation, Hallucination, NLI and Prompt-Injection Tasks

Large language models (LLMs) are widely used as judges for content moderation, hallucination detection and prompt-injection filtering, although they are slow, expensive and poorly calibrated when asked to verbalise probabilities. We evaluate a different design point: a commercially served decision-only model (typesafe/...

A general convergence theorem for nearest-element recurrences

Let b(n) be a strictly increasing sequence of positive integers satisfyinglim_{n→∞} b(n+1)/b(n) = 1. Define a recurrence by taking a_n to be the element of b nearest to a_{n-1} + a_{n-2}, with ties broken by taking the smaller element. We prove that for any initial values a_1, a_2 in b, lim_{n→∞} a_n / a_{n-1} = φ := (...

Generative Artificial Intelligence in Cartographic Production: Evaluation of Large Language Models for Map Generation at Different Levels of Prompt Complexity

Artificial Intelligence in Geospatial Data Processing and Analysis -> Knowledge representation and geospatial data handling with Multimodal Language Models and Agentic Systems

Calibrated Confidence Expression for Radiology Report Generation

ConRad (Confidence Calibration for Radiology Reports), a reinforcement learning framework for fine-tuning medical LVLMs to produce calibrated verbalized confidence estimates alongside radiology reports, is introduced and substantially improves calibration and outperforms competing methods.

Mapping applications and evaluations of LLM-enabled AI chatbots for health purposes: a scoping review

Empirical studies of LLM-enabled AI chatbot applications and evaluations for health purposes across four stakeholder groups: the public or patients, health professionals, health researchers and students, and health institutions are mapped.