Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.23908 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910982128795648 |
|---|---|
| author | Zhu, Winstead Clifton, Ann Ghazimatin, Azin Tanaka, Edgar Ronan, Edward |
| author_facet | Zhu, Winstead Clifton, Ann Ghazimatin, Azin Tanaka, Edgar Ronan, Edward |
| contents | Discovering and evaluating long-form talk content such as videos and podcasts poses a significant challenge for users, as it requires a considerable time investment. Previews offer a practical solution by providing concise snippets that showcase key moments of the content, enabling users to make more informed and confident choices. We propose an LLM-based approach for generating podcast episode previews and deploy the solution at scale, serving hundreds of thousands of podcast previews in a real-world application. Comprehensive offline evaluations and online A/B testing demonstrate that LLM-generated previews consistently outperform a strong baseline built on top of various ML expert models, showcasing a significant reduction in the need for meticulous feature engineering. The offline results indicate notable enhancements in understandability, contextual clarity, and interest level, and the online A/B test shows a 4.6% increase in user engagement with preview content, along with a 5x boost in processing efficiency, offering a more streamlined and performant solution compared to the strong baseline of feature-engineered expert models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_23908 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Transforming Podcast Preview Generation: From Expert Models to LLM-Based Systems Zhu, Winstead Clifton, Ann Ghazimatin, Azin Tanaka, Edgar Ronan, Edward Information Retrieval H.4.0 Discovering and evaluating long-form talk content such as videos and podcasts poses a significant challenge for users, as it requires a considerable time investment. Previews offer a practical solution by providing concise snippets that showcase key moments of the content, enabling users to make more informed and confident choices. We propose an LLM-based approach for generating podcast episode previews and deploy the solution at scale, serving hundreds of thousands of podcast previews in a real-world application. Comprehensive offline evaluations and online A/B testing demonstrate that LLM-generated previews consistently outperform a strong baseline built on top of various ML expert models, showcasing a significant reduction in the need for meticulous feature engineering. The offline results indicate notable enhancements in understandability, contextual clarity, and interest level, and the online A/B test shows a 4.6% increase in user engagement with preview content, along with a 5x boost in processing efficiency, offering a more streamlined and performant solution compared to the strong baseline of feature-engineered expert models. |
| title | Transforming Podcast Preview Generation: From Expert Models to LLM-Based Systems |
| topic | Information Retrieval H.4.0 |
| url | https://arxiv.org/abs/2505.23908 |