Mingchuan Yang

large language model (3) few-shot learning (1) chain-of-thought reasoning (1) text generation (1) language modeling (1) preference optimization (1) instruction following (1) reinforcement learning from human feedback (1) constraint satisfaction (1) adversarial attack (1) feedback loop (1) reward hacking (1) language model (1) reward signal (1) dialog generation (1) contrastive decoding (1) llm alignment (1) reward optimization (1) adversarial preference learning (1) model refinement (1)