2 papers
cs.CL2026
Low-Resource Safety Failures Are Action Failures, Not Representation Failures
Rashad Aziz, Ikhlasul Akmal Hanif, Fajri Koto
Safety alignment learned in high-resource languages transfers poorly to low-resource languages. Models refuse harmful prompts in English but fail to refuse when the same prompts ar…
cs.CL2026
CA-BED: Conversation-Aware Bayesian Experimental Design
Daniel Arnould, Rashad Aziz, Zixuan Kang +5
Large Language Models (LLMs) excel at static reasoning tasks, yet their performance often degrades in interactive scenarios where information must be actively acquired through ques…