3 citations · 3 across the 9 of their papers we have counts for
4 papers · 1 filter
Multilingual GSM-Symbolic: What determines capability transfer across languages?
Kenneth Enevoldsen, Riley Herchert, Sofie Mosegaard +22
We understand little about how capabilities acquired in one language carry over to another, or what governs this transfer: evaluations rely on incomparable, saturation-prone datase…
Belief Propagation in LLM World Models: Measuring Strategic Information Bias with Prediction Markets
Mykola Khandoga, Yevhen Kostiuk, Anton Polishko +4
Every information ecosystem produces beliefs that shape strategic decisions. Both human analysts and AI systems inherit the blind spots of their information sources. We show that L…
Naturalistic measure of social norms alignment
Yevhen Kostiuk, Kenneth Enevoldsen, Peter Bjerregaard Vahlstrup +2
Social norms reflect shared expectations on acceptable behavior. Measuring social norms alignment remains challenging, with existing approaches typically relying on artificial clos…
One prompt is not enough: Instruction Sensitivity Undermines Embedding Model Evaluation
Yevhen Kostiuk, Kenneth Enevoldsen
Instruction embedding models have become common among state-of-the-art models, however are evaluated using a single prompt per task. The single-point evaluation ignores a main prob…