MetaKP: On-Demand Keyphrase Generation

TL;DR

MetaKP introduces on-demand keyphrase generation tailored to specific goals, utilizing a large benchmark and innovative prompting methods to improve performance and adaptability across domains.

Contribution

The paper presents MetaKP, a new benchmark and methods for on-demand keyphrase generation that adapt to user goals, including a novel self-consistency prompting approach with large language models.

Findings

Self-consistency prompting with GPT-4o outperforms fine-tuned models.

Performance drops under distribution shifts for supervised methods.

MetaKP enables applications like epidemic event detection.

Abstract

Traditional keyphrase prediction methods predict a single set of keyphrases per document, failing to cater to the diverse needs of users and downstream applications. To bridge the gap, we introduce on-demand keyphrase generation, a novel paradigm that requires keyphrases that conform to specific high-level goals or intents. For this task, we present MetaKP, a large-scale benchmark comprising four datasets, 7500 documents, and 3760 goals across news and biomedical domains with human-annotated keyphrases. Leveraging MetaKP, we design both supervised and unsupervised methods, including a multi-task fine-tuning approach and a self-consistency prompting method with large language models. The results highlight the challenges of supervised fine-tuning, whose performance is not robust to distribution shifts. By contrast, the proposed self-consistency prompting approach greatly improves the performance of large language models, enabling GPT-4o to achieve 0.548 SemF1, surpassing the performance of a fully fine-tuned BART-base model. Finally, we demonstrate the potential of our method to serve as a general NLP infrastructure, exemplified by its application in epidemic event detection from social media.