4 papers
SciPaths: Forecasting Pathways to Scientific Discovery
Eric Chamoun, Yizhou Chi, Yulong Chen +4
Scientific progress depends on sequences of enabling contributions, yet existing AI4Science benchmarks largely focus on citation prediction, literature retrieval, or idea generatio…
Mitigating Shortcut Learning with InterpoLated Learning
Michalis Korakakis, Andreas Vlachos, Adrian Weller
Empirical risk minimization (ERM) incentivizes models to exploit shortcuts, i.e., spurious correlations between input attributes and labels that are prevalent in the majority of th…
Representational Alignment Supports Effective Machine Teaching
Ilia Sucholutsky, Katherine M. Collins, Maya Malaviya +11
A good teacher should not only be knowledgeable, but should also be able to communicate in a way that the student understands -- to share the student's representation of the world.…
ALVIN: Active Learning Via INterpolation
Michalis Korakakis, Andreas Vlachos, Adrian Weller
Active Learning aims to minimize annotation effort by selecting the most useful instances from a pool of unlabeled data. However, typical active learning methods overlook the prese…