arXiv subjects

Benjamin Chua

Publications and source records attributed to Benjamin Chua.

3 recordsLinked to original sources

arXiv2026

Magnetic resonance imaging assessment of the suitability and consistency of radiotherapy treatment positioning achieved using intra-oral stents

As head-and-neck radiotherapy treatments grow more complex and precise, it becomes increasingly important to assess the anatomical separations that can be achieved using intra-oral stents. A series of twenty T2-weighted turbo spin echo magnetic resonance images (MRI) were acquired of one healthy participant, with a range of different wax and 3D printed intra-oral stents in situ. The resulting measurements showed that a 3D printed modular stent containing hard polylactic acid (PLA) and flexible thermoplastic polyurethane (TPU) components made the largest and most reproducible separation between the cheeks (70.8 +/- 0.3 mm), two hard PLA stents designed to exactly fit the participant's teeth produced the poorest positioning reproducibility (standard deviations of up to 3 mm between a range of landmarks measured in repeated images). Most stents were described as ``comfortable'' although the wax stents left small pieces of wax attached to the teeth after use. This MRI based comparison demonstrated that the materials and designs used for intra-oral stents can have substantial effects on the level of anatomical separation and positioning reproducibility that they produce.

physics.med-ph↗

arXiv2026

Improving Methodologies for Agentic Evaluations Across Domains: Leakage of Sensitive Information, Fraud and Cybersecurity Threats

The rapid rise of autonomous AI systems and advancements in agent capabilities are introducing new risks due to reduced oversight of real-world interactions. Yet agent testing remains nascent and is still a developing science. As AI agents begin to be deployed globally, it is important that they handle different languages and cultures accurately and securely. To address this, participants from The International Network for Advanced AI Measurement, Evaluation and Science, including representatives from Singapore, Japan, Australia, Canada, the European Commission, France, Kenya, South Korea, and the United Kingdom have come together to align approaches to agentic evaluations. This is the third exercise, building on insights from two earlier joint testing exercises conducted by the Network in November 2024 and February 2025. The objective is to further refine best practices for testing advanced AI systems. The exercise was split into two strands: (1) common risks, including leakage of sensitive information and fraud, led by Singapore AISI; and (2) cybersecurity, led by UK AISI. A mix of open and closed-weight models were evaluated against tasks from various public agentic benchmarks. Given the nascency of agentic testing, our primary focus was on understanding methodological issues in conducting such tests, rather than examining test results or model capabilities. This collaboration marks an important step forward as participants work together to advance the science of agentic evaluations.

cs.AI↗

arXiv2026

Improving Methodologies for LLM Evaluations Across Global Languages

As frontier AI models are deployed globally, it is essential that their behaviour remains safe and reliable across diverse linguistic and cultural contexts. To examine how current model safeguards hold up in such settings, participants from the International Network for Advanced AI Measurement, Evaluation and Science, including representatives from Singapore, Japan, Australia, Canada, the EU, France, Kenya, South Korea and the UK conducted a joint multilingual evaluation exercise. Led by Singapore AISI, two open-weight models were tested across ten languages spanning high and low resourced groups: Cantonese English, Farsi, French, Japanese, Korean, Kiswahili, Malay, Mandarin Chinese and Telugu. Over 6,000 newly translated prompts were evaluated across five harm categories (privacy, non-violent crime, violent crime, intellectual property and jailbreak robustness), using both LLM-as-a-judge and human annotation. The exercise shows how safety behaviours can vary across languages. These include differences in safeguard robustness across languages and harm types and variation in evaluator reliability (LLM-as-judge vs. human review). Further, it also generated methodological insights for improving multilingual safety evaluations, such as the need for culturally contextualised translations, stress-tested evaluator prompts and clearer human annotation guidelines. This work represents an initial step toward a shared framework for multilingual safety testing of advanced AI systems and calls for continued collaboration with the wider research community and industry.

cs.AI↗