LED down the rabbit hole: exploring the potential of global attention for biomedical multi-document summarisation

Specifically, we adapt PRIMERA (Xiao et al., 2022) to Overall, our contributions in comparison to the previously published domain-specific models In this paper we describe our experiments and results for MDS are the following: on the Multidocument Summarisation for Literature Review (MSLR) shared task. In particular, We explore the potential of using global attention we attempt to improve on previous multi-document as a means to highlight important biomedical summarisation models in the biomedical domain, entities, in order to improve aggregation which have tried to integrate domain knowledge across input documents.