Sruthi Kuriakose

Train­ing Lan­guage Models for Con­trol­led Stochasticity

Sys­tem­atic run­away-op­ti­miser-like LLM failure modes on Biolog­i­cally and Eco­nom­i­cally al­igned AI safety bench­marks for LLMs with sim­plified ob­ser­va­tion for­mat (BioBlue)