PPL
Chengshuai Shi
Papers (4)
Is One Score Enough? Rethinking the Evaluation of Sequentially Evolving LLM MemoryEfficient Multi-objective Prompt Optimization via Pure-exploration BanditsContinual Harness: Online Adaptation for Self-Improving Foundation Agents$f$-Divergence Regularized RLHF: Two Tales of Sampling and Unified Analyses