Lirong Gao

large language model (3) uncertainty quantification (1) knowledge transfer (1) in-context learning (1) natural language generation (1) natural language understanding (1) model adaptation (1) uncertainty estimation (1) parameter-efficient tuning (1) retrieval-augmented generation (1) reasoning model (1) process reward (1) black-box model (1) attention pruning (1) demonstration selection (1) retrieval-based method (1) retrieval-based learning (1) outcome reward (1) reinforcement learning (1) prompt recovery (1)