5 papers
Oracle-Guided Soft Shielding for Safe Move Prediction in Chess
Prajit T Rajendran, Fabio Arnez, Huascar Espinoza +2
In high stakes environments, agents relying purely on imitation learning or reinforcement learning often struggle to avoid safety-critical errors during exploration. Existing reinf…
Improving Methodologies for LLM Evaluations Across Global Languages
Akriti Vij, Benjamin Chua, Darshini Ramiah +43
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…
Improving Methodologies for Agentic Evaluations Across Domains: Leakage of Sensitive Information, Fraud and Cybersecurity Threats
Ee Wei Seah, Yongsen Zheng, Naga Nikshith +67
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 rema…
The Singapore Consensus on Global AI Safety Research Priorities
Yoshua Bengio, Tegan Maharaj, Luke Ong +84
Rapidly improving AI capabilities and autonomy hold significant promise of transformation, but are also driving vigorous debate on how to ensure that AI is safe, i.e., trustworthy,…
Empowering the trustworthiness of ML-based critical systems through engineering activities
Juliette Mattioli, Agnes Delaborde, Souhaiel Khalfaoui +3
This paper reviews the entire engineering process of trustworthy Machine Learning (ML) algorithms designed to equip critical systems with advanced analytics and decision functions.…