Search papers, labs, and topics across Lattice.
5
1
8
8
Static profiles lead to identity essentialism in LLMs, but a new longitudinal memory framework reveals a path to richer, more diverse social simulations.
Despite high retrieval rates, LLMs miss over 47% of relevant studies in meta-analysis, exposing a critical gap in their systematic reasoning capabilities.
Current LLM judges show a troubling reliability gap in long-form evaluations, raising questions about their effectiveness in real-world applications.
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.
