Multi-document scientific summarization can extract and organize important
information from an abundant collection of papers, arousing widespread
attention recently. However, existing efforts focus on producing lengthy
overviews lacking a clear and logical hierarchy. To alleviate this problem, we
present an atomic and challenging task named Hierarchical Catalogue Generation
for Literature Review (HiCatGLR), which aims to generate a hierarchical
catalogue for a review paper given various references. We carefully construct a
novel English Hierarchical Catalogues of Literature Reviews Dataset (HiCaD)
with 13.8k literature review catalogues and 120k reference papers, where we
benchmark diverse experiments via the end-to-end and pipeline methods. To
accurately assess the model performance, we design evaluation metrics for
similarity to ground truth from semantics and structure. Besides, our extensive
analyses verify the high quality of our dataset and the effectiveness of our
evaluation metrics. Furthermore, we discuss potential directions for this task
to motivate future research.

本研究以文獻綜述的目錄生成為挑戰，構建了涵蓋 13.8k 個目錄和 120k 個參考文獻的英文文獻綜述目錄數據集，並通過端到端和管線方法進行了多方面的評估與分析，提出了基於語義和結構相似度的模型性能評估方式。結果顯示，本研究提出的生成方法與評估指標具有較高的效果和品質，並且為以後的相關研究提供了方向。