Learning to Explore and Select for Coverage-Conditioned Retrieval-Augmented Generation

Understand

Interactions with large language models (LLMs) often yield long and detailed responses, leveraging both parametric knowledge and retrieval-augmented generation (RAG).

• While these responses can provide rich insights, they often include redundant or less engaging content not aligned with user interests.
• This issue becomes apparent when users specify particular subtopics to include or exclude -- termed coverage-conditioned ($C^2$) queries -- as LLMs often struggle to provide tailored responses.
• To address this challenge, we investigate the role of query outlines, sequences of subqueries designed to guide LLMs in generating responses that meet specific user requirements.