large language models

Consistent Explainers or Unreliable Narrators: Systematic Differences in Consistency and Sensitivity Across Large Language Models for Group Recommendations

Group Recommender Systems (GRS) face the challenge of combining conflicting individual preferences. While Large Language Models (LLMs) are increasingly integrated into GRS, they may introduce risks regarding output inconsistency or sensitivity to group characteristics. In this paper, we analyze LLMs acting as both deci...

Do we carry the false belief that LLMs have a theory of mind?

Reprezentacja informacji proweniencyjnych w internetowych katalogach muzealnych a wykorzystanie dużych modeli językowych

The article analyses how the representation of provenance information in online museum catalogues affects its identification and extraction by modern large language models (LLMs). The study examined 60 painting records from four Polish museums using the GPT-5.5 model. Six basic methods of representing provenance inform...

An interpretable large language model framework with the cokemaking-oriented prompt and fuzzy-enhanced explanation for coke quality prediction

Politeness to ChatGPT Reconsidered: Structural Injustice and Respect for Rational Agents

The widespread interaction between humans and large language models has sparked normative debates regarding user politeness toward artificial intelligence. This paper explores the ethical rationality of maintaining polite linguistic norms in human-LLM interaction, arguing against the normative obligation of being polit...

Design and Deployment of Custom GPT Solutions Using Azure OpenAI Service

Enterprise adoption of Large Language Models demands evaluation beyond model accuracy, encompassing cost, latency, compliance, and update adaptability. This paper introduces a Quantitative Evaluation Framework (QEF) to benchmark GPT deployment strategies within Azure OpenAI infrastructure. Five configurations baseline...

Effects of proactivity, autonomy, and transparency on user perception in human-AI agent interactions

As large language model-driven AI agents evolve from generative tools into collaborative entities with autonomous capabilities, the human-AI interaction paradigm is shifting from command execution to task delegation. However, empirical evidence on how the behavioral characteristics of AI agents reshape user perception...

Hi-SCCG: Hierarchical Structure-aware Chunking and Context Generation for document-level information extraction

Large Language Model (LLM)-based generative Information Extraction (IE) over long documents is constrained by finite context windows, and the necessary text-chunking step disrupts semantic continuity, causing subject drift, unresolved coreference, and loss of the global constraints required for fine-grained knowledge g...

InfiniLoRA: Disaggregated Multi-LoRA Serving for Large Language Models

LoRA enables efficient customization of LLMs and is widely used in multi-tenant and multi-task serving. However, emerging model architectures such as MoE significantly increase LoRA memory cost, making existing coupled LoRA serving designs poorly scalable and prone to tail-latency inflation. We present InfiniLoRA, a di...

Disentangling interaction and bias effects in opinion dynamics of large language models

Abstract Large Language Models are increasingly used to simulate human opinion dynamics, yet the effect of genuine interaction is often obscured by systematic biases. We develop a Bayesian framework to disentangle and quantify three such biases: (i) A topic bias toward the LLM’s default stance; (ii) an agreement bias f...

Graph-Enhanced Retrieval-Augmented Generation for Postoperative Patient Question Answering: A Comparative Evaluation of Knowledge Graph, Retrieval-Augmented Generation, and Hybrid GraphRAG Approaches

GraphRAG is a multi-component pipeline that also includes query expansion, a second retrieval stage, evidence fusion, and a monotonic RAG fallback, and is therefore evaluated as a complete hybrid system rather than as graph retrieval in isolation, which reflects the complete hybrid system rather than graph augmentation...

Computational Approaches to Penicillin Allergy De-labelling: A Clinical Review

Penicillin allergy is recorded in roughly one in ten hospital patients, yet fewer than one in ten of those records reflects a real, clinically significant allergy. The mismatch matters: patients with a penicillin label receive more second-line and broader-spectrum antibiotics, with measurable downstream costs in infect...