Learning to Explore and Select for Coverage-Conditioned Retrieval-Augmented Generation
This work addresses the issue of user-specific content alignment in LLM interactions, though it is incremental as it builds on existing RAG and query planning methods.
The paper tackles the problem of large language models (LLMs) producing redundant or misaligned responses in coverage-conditioned retrieval-augmented generation (RAG) scenarios by introducing query outlines to guide tailored responses, resulting in QPlanner, a 7B model that generates higher-quality outlines as shown through automatic and human evaluations.
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. To systematically create and evaluate these outlines, we introduce QTree, a dataset of 10K hierarchical sets of information-seeking subqueries that define structured boundaries for outline creation and evaluation in $C^2$ scenarios. Additionally, we develop QPlanner, a 7B language model trained to generate customized outlines within boundaries of QTree. We evaluate the effectiveness of the generated outlines through automatic and human judgements, focusing on their impact within retrieval-augmented generation (RAG) systems. Experimental results demonstrate that QPlanner, especially when trained with alignment techniques like DPO, generates higher-quality outlines that better fulfill diverse user needs.