190 citations
- Cardiff UniversityGB7 papers
- Microsoft Research (United Kingdom)GB3 papers
- Rochester Institute of TechnologyUS2 papers
- University of AllahabadIN2 papers
- University of BirminghamGB2 papers
- University of CambridgeGB2 papers
- University of South WalesGB2 papers
- University of Wales Institute CardiffSG2 papers
- Adobe Systems (United States)US1 paper
- ARC Centre of Excellence for Gravitational Wave DiscoveryAU1 paper
- Beijing Tongren HospitalCN1 paper
- California Institute of TechnologyUS1 paper
4 papers · 1 filter
Operational Hallucination and Safety Drift in AI Agents
Shasha Yu, Fiona Carroll, Barry L. Bentley
Large language models (LLMs) serving as planners in tool-using autonomous agents introduce dynamic reliability risks in multi-turn execution. While single-turn safety mechanisms ar…
Rethinking AI Literacy Education in Higher Education: Bridging Risk Perception and Responsible Adoption
Shasha Yu, Fiona Carroll, Barry L. Bentley
As AI becomes increasingly embedded across societal domains, understanding how future AI practitioners, particularly technology students, perceive its risks is essential for respon…
The Causal Impact of Tool Affordance on Safety Alignment in LLM Agents
Shasha Yu, Fiona Carroll, Barry L. Bentley
Large language models (LLMs) are increasingly deployed as agents with access to executable tools, enabling direct interaction with external systems. However, most safety evaluation…
Atomic-resolution imaging of gold species at organic liquid-solid interfaces
Sam Sullivan-Allsop, Nick Clark, Wendong Wang +26
Understanding solid-liquid interfaces at the atomic-scale is key to improved performance of heterogeneous catalysts, electrodes and membranes. Here we combine unique specimen desig…