Summaries, Highlights, and Action items: Design, implementation and evaluation of an LLM-powered meeting recap system

Meetings play a critical infrastructural role in coordinating work. The recent surge of hybrid and remote meetings in computer-mediated spaces has led to new problems (e.g., more time spent in less engaging meetings) and new opportunities (e.g., automated transcription/captioning and recap support). Recent advances in language understanding for dialog summarization can potentially generate helpful recaps to improve the post-meeting experience for personal and group work. Despite this potential, a single fixed-length summary of the entire meeting may not serve diverse needs, such as quick takeaways or their use for an in-depth understanding of meeting discussions. To address these gaps, we use cognitive science and discourse theories to conceptualize two recap designs: important highlights and a structured, hierarchical minutes view, targeting complementary recap needs. We operationalize these representations into high-fidelity prototypes using dialogue summarization. Finally, we evaluate the representations' effectiveness with seven users in the context of their work meetings. Our findings indicate the need for both representations in different contexts. We identify post-meeting collaboration opportunities like discussions or achieving consensus enabled by the recaps. Exploring the meaning of users adding, editing, and deleting from recaps suggests varying alignment for using these actions to improve AI-recap. Our design implications, such as incorporating organizational artifacts (e.g., linking presentations) in recaps and personalizing context, advance the discourse of effective recap designs for organizational work and support past results from cognition studies.