Presentations by the Humans and For the Humans: Harnessing LLMs for Generating Persona-Aware Slides from Documents

Ishani Mondal, Shwetha S, Anandhavelu Natarajan, Aparna Garimella, Sambaran Bandyopadhyay, Jordan Lee Boyd-Graber

Main: NLP Applications Oral Paper

Session 6: NLP Applications (Oral)
Conference Room: Marie Louise 2
Conference Time: March 19, 10:30-12:00 (CET) (Europe/Malta)
TLDR:
You can open the #paper-411-Oral channel in a separate window.
Abstract: Scientific papers and slides are two different representations of the same underlying information, but both require substantial work to prepare. While there had been prior efforts on automating document-to-slides generation, there is still a pressing need of customizing the presentation of content aligning with the persona of target audience or duration of presentation. This paper first introduces the concept of end-user specification-aware document to slides conversion that incorporates end-user specifications into the conversion process. For this, we initially introduce a new dataset reuse the existing SciDuet dataset consisting of pairs of papers and corresponding slides decks from recent years’ *ACL conferences to create four persona-aware configurations. Secondly, we present Persona-Aware-D2S, a novel approach by finetuning LLMs using target audience feedback to create persona-aware slides from scientific documents. Our evaluation on both automated metrics and qualitative human evaluation suggests that by incorporating end-user specifications into the conversion process, our model can create presentations that are not only informative but also tailored to expectations and cognitive abilities of target audience.