Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Trait-space Monitoring for Emergent Misalignment During Supervised Finetuning
Huy Nghiem, Sy-Tuyen Ho, Sarah Wiegreffe +1
Emergent misalignment (EM) occurs when narrow finetuning induces dangerous behavior outside the finetuning task. Detecting this shift through repeated behavioral evaluation is cost…
cs.LG2026
SoundnessBench: Can Your AI Scientist Really Tell Good Research Ideas from Bad Ones?
Sy-Tuyen Ho, Minghui Liu, Huy Nghiem +6
Autonomous AI research agents aim to speed up scientific discovery by automating the research pipeline from hypothesis generation to peer review. However, existing benchmarks rarel…