QD-Rec: Open-Ended Recommendations via Quality-Diversity
In brief
- QD-Rec produces recommendations with natural-language justifications using a foundation model.
- The approach balances diversity and quality via a dynamic archive of solutions.
- Tested on M&A, customer targeting, and paper/book recommendations, it outperforms baselines.
This study introduces QD-Rec, a novel method for generating diverse, high-quality recommendations by combining open-ended search with foundation models. It targets decisions where possible choices are fixed but their justifications remain to be explored.
This summary gives you the essentials. The full article, its figures and quotes are on cs.AI updates on arXiv.org.
Read the original articleAI-generated summary of the source, checked by rules. Report an error