Prompting LLMs with content plans to enhance the summarization of scientific articles
This work addresses the problem of improving summarization for scientific articles, offering an incremental approach to enhance less powerful systems.
The paper tackles the challenge of summarizing scientific articles by introducing prompting techniques that provide key terms as contextual guidance, resulting in performance gains especially for smaller models.
This paper presents novel prompting techniques to improve the performance of automatic summarization systems for scientific articles. Scientific article summarization is highly challenging due to the length and complexity of these documents. We conceive, implement, and evaluate prompting techniques that provide additional contextual information to guide summarization systems. Specifically, we feed summarizers with lists of key terms extracted from articles, such as author keywords or automatically generated keywords. Our techniques are tested with various summarization models and input texts. Results show performance gains, especially for smaller models summarizing sections separately. This evidences that prompting is a promising approach to overcoming the limitations of less powerful systems. Our findings introduce a new research direction of using prompts to aid smaller models.