Q-STRUM Debate: Query-Driven Contrastive Summarization for Recommendation Comparison
This work addresses a problem for users needing to understand recommendations, but it is incremental as it extends an existing method.
The paper tackled the challenge of query-driven recommendation with unknown items by introducing Q-STRUM Debate, a method that uses debate-style prompting to generate contrastive summaries, resulting in significant performance improvements over existing methods on key criteria across three datasets.
Query-driven recommendation with unknown items poses a challenge for users to understand why certain items are appropriate for their needs. Query-driven Contrastive Summarization (QCS) is a methodology designed to address this issue by leveraging language-based item descriptions to clarify contrasts between them. However, existing state-of-the-art contrastive summarization methods such as STRUM-LLM fall short of this goal. To overcome these limitations, we introduce Q-STRUM Debate, a novel extension of STRUM-LLM that employs debate-style prompting to generate focused and contrastive summarizations of item aspects relevant to a query. Leveraging modern large language models (LLMs) as powerful tools for generating debates, Q-STRUM Debate provides enhanced contrastive summaries. Experiments across three datasets demonstrate that Q-STRUM Debate yields significant performance improvements over existing methods on key contrastive summarization criteria, thus introducing a novel and performant debate prompting methodology for QCS.