2 papers
cs.CR2026
Minionese: Comprehensive Benchmark and Mechanistic Study of Multilingual LLM Safety
Chigozirim Ifebi, Brent Kong, Ayushi Mehrotra
Safety alignment in large language models remains brittle across languages: prompts reliably refused in English can elicit harmful compliance in non-English and low-resource settin…
cs.LG2026
AlphaZero in Sparsely Rewarded Games: Limits and Auxiliary Supervision
Brent Kong, Tejas Ram, Tony Yue Yu
AlphaZero has demonstrated that a neural-guided Monte Carlo Tree Search can achieve superhuman performance, but strong play does not necessarily imply perfect play. We study this g…