Siwei Wu

commonsense reasoning (3) vision-language model (3) contrastive learning (2) contrastive evaluation (2) knowledge graph completion (2) evaluation metric (2) natural language generation (2) text generation (2) likelihood bia (2) large language model (2) direct preference optimization (1) text summarization (1) summarization evaluation (1) cross-modal retrieval (1) image captioning (1) visual question answering (1) reinforcement learning (1) data annotation (1) instruction tuning (1) commonsense knowledge (1)