Search papers, labs, and topics across Lattice.
Affiliation:
3
0
5
Dataset representation in NLP is alarmingly uneven, with geographic blind spots that could skew AI development and policy.
LLMs can be tricked into unsafe responses to children, but even subtle cues about the user's age can dramatically improve safety.
Beliefs, not just demographics, are a powerful prior for simulating how different groups fall for misinformation, achieving up to 92% accuracy in LLM simulations.
