Browse Articles

An explainable AI framework for studying query complexity and hallucinations in LLM scheduling tasks

Thantron et al. | Nov 09, 2026

An explainable AI framework for studying query complexity and hallucinations in LLM scheduling tasks
Image credit: Immo Wegmann

In this study, we investigated how the complexity of a query can influence tool-use hallucinations in large language models that were tasked with setting an appointment. Using explainable AI (XAI) as a tool to test the hypothesis, we analyzed trends in hallucination rates by the type of query and saw results that when complexity and ambiguity of the query increased (such as asking for multiple days or unclear time ranges), the model was more likely to make errors due to misunderstanding time-related data from tool outputs. This shows that making large language models (LLMs) understand what seems logical to a human is still difficult, especially in complex tasks, and that knowing what causes these errors can help build more trustworthy AI systems.

Read More...

Stereolithography 3D-printed stents with silica and zirconia nanoparticle reinforcement for intracranial aneurysm treatment

Panda et al. | Oct 12, 2026

Stereolithography 3D-printed stents with silica and zirconia nanoparticle reinforcement for intracranial aneurysm treatment
Image credit: Panda, Jeong, and Srinivasan

This manuscript focuses on improving the mechanical strength and radiopacity of SLA 3D-printed stent materials by incorporating nanoparticles for their application in flow-diverting stents (FDSs) used to treat aneurysms. The authors used biocompatible, bioresorbable resin formulations with varying concentrations of silica and zirconium to enhance tensile strength and radiopacity, respectively. The authors employed SEM to confirm the incorporation of nanoparticles, and CT imaging was used to assess the effect of zirconium-infused FDSs.

Read More...

Testing the Impact of a Geometric Curvature Variable on the Accuracy of Econometric Forecasting Models

Punatar et al. | Jul 26, 2026

Testing the Impact of a Geometric Curvature Variable on the Accuracy of Econometric Forecasting Models

Classical financial forecasting models often fail to capture the complex, nonlinear dynamics of the stock market. This study demonstrates that incorporating a single variable to represent the 'geometric curvature' of a time series dramatically improves the accuracy of standard econometric forecasts. Our findings highlight that geometric properties are a significant predictive factor, opening new avenues for more powerful financial modeling.

Read More...