Search papers, labs, and topics across Lattice.
4
1
7
3
Static profiles lead to identity essentialism in LLMs, but a new longitudinal memory framework reveals a path to richer, more diverse social simulations.
ReGrad enables scalable and reversible knowledge injection without the risk of catastrophic forgetting, outperforming traditional methods in both general and domain-specific tasks.
Injecting demographic attributes directly into LLM hidden states can drastically improve the diversity and realism of public opinion simulations.
LLMs still can't convincingly mimic human personas, especially when it comes to syntactic style and memory, despite advancements in other areas.