Search papers, labs, and topics across Lattice.
University of Michigan
3
0
4
Deductive stereotyping in LLMs leads to biased reasoning, but targeted injection phrases can dramatically enhance fairness across diverse tasks.
Misfired alignment in LLMs can lead to a 18.9% failure rate in reasoning about stereotypes, revealing a critical flaw in current safety-oriented training methods.
A single biased example can completely undermine the alignment of large language models, revealing a critical flaw in their post-training safety mechanisms.
