Weaviate Podcast Agentic Topic Modeling with Maarten Grootendorst - Weaviate Podcast #126!
13 snips
Jul 9, 2025 Maarten Grootendorst, a psychologist turned AI engineer known for creating BERTopic, dives into the exciting world of agentic topic modeling. He discusses how large language models (LLMs) are revolutionizing the way we extract and categorize topics from complex data. The conversation highlights the challenges of traditional vs. LLM-driven methods and the critical role of human feedback. Maarten also emphasizes the importance of modularity in BERTopic, allowing for adaptive and efficient topic exploration tailored to user needs.
AI Snips
Chapters
Books
Transcript
Episode notes
Collaborative Book Writing Experience
- Maarten enjoyed co-authoring "Hands-On Large Language Models" with Jay Alammar.
- This collaborative book writing offered rich learning and creative challenges in writing style and visuals.
Subjectivity in Topic Modeling
- Maarten views topic modeling as subjective, varying with user needs for granularity.
- BERTopic's modularity allows users to tailor topic models to their preferences effectively.
Combining Embeddings and LLMs
- Embeddings provide stable, reusable document representations, while LLMs can steer topic extraction more flexibly.
- Combining both could enhance topic modeling by balancing efficiency and fine-grained analysis.
