Zhenjiang Dong

Seeking Rational Demonstrations for Large Language Models: A Domain Generalization Approach to Unsupervised Cross-Domain Keyphrase Generation

Unsupervised cross-domain keyphrase generation is crucial in real-world natural language processing scenarios. However, the accuracy of up-to-date approaches is limited by the distribution shift between source and target domain, which stems from the cross-domain field. Large language models (LLMs) o…