DaLAs Collection This collection groups all versions and variants of the Danish Linguistic Acceptability evaluation dataset (https://arxiv.org/abs/2512.04799) • 9 items • Updated about 6 hours ago
The Arbiter Agent: Continually Monitoring Multi-Agent Conversations to Detect Emergent Misalignment Paper • 2606.10747 • Published Jun 9 • 13
PsychoSafe: Eliciting Psychologically-Informed Refusals in Large Language Models Paper • 2606.09697 • Published Jun 8 • 7 • 4
BrainSurgery: Reproducible and Reliable Declarative Weight Manipulations for Model Editing and Upcycling Paper • 2606.09707 • Published Jun 8 • 8