Search papers, labs, and topics across Lattice.
3
25
6
8
LLMs can achieve 7.32% better goal completion in social negotiations by strategically optimizing reward signals based on dialogue context.
P-GenRM personalizes LLMs more effectively by generating adaptive personas and scoring rubrics from user preferences, outperforming existing reward models by 2.31% and offering a 3% boost via test-time scaling.
DPO's rise as a computationally efficient alternative to RLHF for LLM alignment has spurred a diverse range of research, now systematically organized and analyzed in this comprehensive survey.
