Search for: All records

Generative AI, particularly Large Language Models (LLMs), has revolutionized human-computer interaction by enabling the generation of nuanced, human-like text. This presents new opportunities, especially in enhancing explainability for AI systems like recommender systems, a crucial factor for fostering user trust and engagement. LLM-powered AI-Chatbots can be leveraged to provide personalized explanations for recommendations. Although users often find these chatbot explanations helpful, they may not fully comprehend the content. Our research focuses on assessing how well users comprehend these explanations and identifying gaps in understanding. We also explore the key behavioral differences between users who effectively understand AI-generated explanations and those who do not. We designed a three-phase user study with 17 participants to explore these dynamics. The findings indicate that the clarity and usefulness of the explanations are contingent on the user asking relevant follow-up questions and having a motivation to learn. Comprehension also varies significantly based on users’ educational backgrounds. 

We report a Tuning Fork Scanning Electrochemical Cell Microscopy (TF-SECCM) technique for providing morphological and electrochemical information of single redox-active entities. This new operation configuration of SECCM utilizes an electrolyte-filled nanopipette tip mounted onto a tuning fork force sensor to obtain a precise tip-sample distance control and surface morphological mapping. Redox activities of regions of interest can be investigated by scanning electrode potential by moving the nanopipette to any target regions while maintaining the constant force engagement of the tip with the sample. Using silver nanowires (Ag NWs) as a model system due to their extensive utilization in energy and sensing devices, TF-SECCM provides not only the topography of single Ag NWs but also their distinctive redox activities and catalytic hydrogen evolution reaction (HER) activities and electrolyte anion adsorption/desorption features in contrast to NW bundles and supporting substrate (e.g., indium tin oxide). 

This paper introduces an innovative approach to recommender systems through the development of an explainable architecture that leverages large language models (LLMs) and prompt engineering to provide natural language explanations. Traditional recommender systems often fall short in offering personalized, transparent explanations, particularly for users with varying levels of digital literacy. Focusing on the Advisor Recommender System, our proposed system integrates the conversational capabilities of modern AI to deliver clear, context-aware explanations for its recommendations. This research addresses key questions regarding the incorporation of LLMs into social recommender systems, the impact of natural language explanations on user perception, and the specific informational needs users prioritize in such interactions. A pilot study with 11 participants reveals insights into the system’s usability and the effectiveness of explanation clarity. Our study contributes to the broader human-AI interaction literature by outlining a novel system architecture, identifying user interaction patterns, and suggesting directions for future enhancements to improve decision-making processes in AI-driven recommendations. 

CO 2 reduction reaction (CO 2 RR) is a promising technique for mitigating global warming and storing renewable energy if it can be obtained with a highly selective, efficient, and durable electrocatalyst. Here, we report CO 2 RR catalyzed by Au nanoparticles (NPs) stabilized by pyridines and pyrimidines (e.g., 2-mercaptopyridine (2Mpy), 4-mercaptopyridine (4Mpy), and 2-mercaptopyrimidine (2Mpym)) on a nanostructured carbon-doped TiO 2 nanowire (NanoCOT) electrode, which has been previously reported by our team for electrocatalytic water oxidation. An online gas chromatography (GC) set-up with improved gaseous product sensitivity with real-time pressure monitoring is used to quantify CO and hydrogen products from the Au NP-modified NanoCOT electrode. High CO selectivity is observed at Au-2Mpy coated NanoCOT electrode. CO 2 reduction products are not observed at bare NanoCOT suggesting CO 2 is reduced at the Au nanoparticle sites of the electrode. Moreover, CH 3 OH is not detected at the Au-Mpy/Mpym NPs during rotating ring disk electrode (RRDE) analysis which implies pyridine attached to the Au NPs has no catalytic effects on CO 2 RR as claimed by others in the literature. A durable complete H-cell using a NanoCOT anode and Au NP-NanoCOT cathode electrodes is assembled for complete water splitting, CO 2 RR, and stability test.