Jianfei Ma

language model (3) large language model (3) chinese language (2) few-shot learning (2) reinforcement learning (2) bidirectional attention (2) supervised fine-tuning (1) temporal difference learning (1) contrastive learning (1) language model evaluation (1) value function (1) benchmark evaluation (1) chain-of-thought reasoning (1) uncertainty estimation (1) mathematical problem solving (1) text embedding (1) hallucination detection (1) ai alignment (1) word embedding (1) in-context learning (1)