This work was done during one weekend by research workshop participants and does not represent the work of Apart Research.
Accepted at the 
 research sprint on 
November 27, 2023

Cross-Lingual Generalizability of the SADDER Benchmark

Produced a multi-lingual benchmark for situational awareness based on SADDER. Assessed performance of GPT3.5 Turbo and GPT 4 on 5 languages. Analysed the effect of adding a contextual prefix informing the model of it's AI identity.

Siddhant Arora, Jord Nguyen, Akash Kundu
4th place
3rd place
2nd place
1st place
 by peer review