large language models

Building Code Question-Answering Systems Enhanced by Large Language Models and Knowledge-Graph-Based Retrieval-Augmented Generation

A retrieval-augmented generation system enhanced with a knowledge graph to interpret building codes by leveraging both the semantic content and structural relationships within the documents by leveraging both the semantic content and structural relationships within the documents.

Capability Generalization in Privileged-Execution LLM Agents: A Catalog of Unanticipated Behaviors During Autonomous Network Defense

Large language models are increasingly proposed as autonomous network-defense agents, which requires privileged command execution not scoped to their stated objective. Evaluating a multi-agent LLM framework that proposes, implements, and validates mitigations against replayed adversary emulation, we observed agents exc...

Explainable AI-Driven Intelligent Video Summarization for Next-Generation Video Production and Content Management

This chapter reviews the development of video summarisation using handcrafted features and deep learning models, the recent advances in transformer-based, vision-language, multimodal learning, and large language models for video summarisation. It introduces the main steps of the summarization pipeline: keyframes extrac...

Can candidates trust a confident answer? Free and paid large language models on dental specialty examination questions

Response-level dataset and analysis code for a study of stated confidence and repeated-query consistency in seven large language models answering the oral and maxillofacial radiology questions of the Turkish Dental Specialty Examination (DUS), 2012–2026. Seven models from four vendors, including three pairs available a...

Managing Vector Data for Retrieval Augmented Generation@Dagstuhl Seminar Summary

This report summarizes discussions that took place in the context of a Dagstuhl seminar1 to explore the emerging paradigm of AI-native databases designed to support agentic workflows and Retrieval-Augmented Generation (RAG) by integrating Large Language Models (LLMs) with robust database abstractions. The central synth...

Adaptive Learning and Collaborative Self-Adaptive Learning Between Self-and-Interaction Models: A Unified Framework for Adaptive Mode Switching

Learning systems often face a fundamental design choice between adapting independently and adapting through collaboration. Independent adaptation allows a model to preserve its autonomy, exploit its own experience, and avoid unnecessary coordination costs. Collaborative adaptation allows multiple models to exchange inf...

A REPRODUCIBLE FRAMEWORK FOR EVALUATING ROMANIZED SINDHI OUTPUT CONSISTENCY IN CONVERSATIONAL LARGE LANGUAGE MODELS: PILOT EVIDENCE FROM REPEATED PROMPTING

LLMs for Pull Request Acceptance Prediction and Flag Identification: An Annotated Dataset and Evaluation (replication package)

Replication package for a study of whether large language models can predict pull request acceptance and identify the green (positive) and red (negative) flags that human annotators associate with a PR’s outcome. The dataset, provided as FINAL_DATASET_FIXED.csv, contains 300 manually annotated PR–issue pairs from six o...

Clinician Use of an Artificial Intelligence–Enabled Clinical Information Platform

Importance Despite growing interest in the use of artificial intelligence (AI) in medicine, empirical evidence on how clinicians use these tools is limited. Objective To characterize clinician use of an AI-enabled clinical information platform, the distribution of use across the clinical workforce, and the purpose of s...

From ethics to metrics: the transformation of corporate social responsibility from good intentions to governance in SME sustainability research

This study examines the development of research on Corporate Social Responsibility (CSR), corporate sustainability, and Environmental, Social, and Governance (ESG) within the context of small and medium-sized enterprises (SMEs). It analyzes 3,168 English-language research articles published from 1959 to 2025, sourced f...

MASK-OFF: evaluating LLMs for omission of material fact

Large language models (LLMs) are widely deployed with the ability to influence user decisions, yet on benign requests they often fail to accurately convey material information, which can lead to harm. While existing benchmarks measure aspects of trustworthiness in LLMs (e.g., hallucination or sycophancy), material omis...

Listen. Answer. Memorize. Building and Running Verified Learning Paths for Geoscience Self-Study with an AI Assistant

Abstract. AI tutors built on large language models can state things that no source supports, a risk that weighs on self-study. This paper describes how a single adult learner built, with an AI assistant, learning paths from his own verified fact documents in the geosciences and, for two of the five cases, learned them...