Search papers, labs, and topics across Lattice.
Monash University
3
0
4
TriAlign achieves a remarkable balance between universal truth consistency and personalized responses, addressing a critical gap in LLM alignment.
Forget costly training or reward models: MATO unlocks personalized LLM alignment by optimizing objective weights *during* generation, offering unprecedented control and adaptability.
LLMs struggle to balance task completion with cultural norms in dynamic social simulations, revealing critical gaps in their cross-cultural robustness and highlighting the need for human oversight in automated benchmarking.
