Search papers, labs, and topics across Lattice.
AWS Generative AI Innovation Center, Amazon Web Services, Stanford University Code: SubramanyamSahoo/Collapse-of-Safety-Classifiers-under-Embedding-Drift Correspondence: sahoo2vec@gmail.com
Amazon Science1
1
3
5
LLMs evaluating job candidates exhibit significant bias against hedging language, docking candidates by 25.6% on average, even when the content is equivalent.
