Yunjia Qi

large language model (3) reward modeling (2) reinforcement learning (2) instruction following (2) natural language inference (1) event understanding (1) language model training (1) policy learning (1) reinforcement learning from human feedback (1) parameter-efficient fine-tuning (1) low-rank adaptation (1) hallucination mitigation (1) human preference (1) high-rank adaptation (1) factuality detection (1) event argument (1) event factuality (1) subnetwork localization (1) gradient sparsity (1) verifiable signal (1)