Summary of Tell Me What I Need to Know: Exploring Llm-based (personalized) Abstractive Multi-source Meeting Summarization, by Frederic Kirstein and Terry Ruas and Robert Kratel and Bela Gipp
Tell me what I need to know: Exploring LLM-based (Personalized) Abstractive Multi-Source Meeting Summarization
by Frederic Kirstein, Terry Ruas, Robert Kratel, Bela Gipp
First submitted to arxiv on: 18 Oct 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper addresses the challenge of meeting summarization by introducing a three-stage large language model approach that considers supplementary materials like presentation slides. The method identifies transcript passages needing context, infers relevant details from supplementary files, inserts them into the transcript, and generates a summary. This multi-source approach enhances model understanding, increasing summary relevance by ~9% and producing more content-rich outputs. Additionally, the paper introduces a personalization protocol that extracts participant characteristics and tailors summaries accordingly, improving informativeness by ~10%. The work also explores performance-cost trade-offs across four leading model families, including edge-device capable options. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research helps make meeting notes better by using extra information like slides to create personalized summaries. Right now, computers struggle to understand the context of a meeting and what’s important. This paper introduces a new way to do this by looking at both the transcript (what was said) and additional files like slides. This approach makes the summary more accurate and detailed, and it can also be used to make summaries just for specific people based on who was in the meeting. |
Keywords
» Artificial intelligence » Large language model » Summarization
