Search papers, labs, and topics across Lattice.
University of Michigan, University of Cambridge University of Aberdeen
2
0
5
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.
Even state-of-the-art models like Gemini and Claude can completely miss critical user information when it's buried in semantically unrelated past interactions, tanking personalization performance.
