# Principled Content Selection to Generate Diverse and Personalized Multi-Document Summaries Source: [Principled Content Selection to Generate Diverse and Personalized Multi-Document Summaries]() Collection index: [llms.txt]() Data updated: 2026-01-02T10:04:09.715Z Authors: Vishakh Padmakumar, Zichao Wang, David Arbour, Jennifer Healey Published: 2025-05-28T01:12:50.000Z ## Abstract While large language models (LLMs) are increasingly capable of handling longer contexts, recent work has demonstrated that they exhibit the "lost in the middle" phenomenon (Liu et al., 2024) of unevenly attending to different parts of the provided context. This hinders their ability to cover diverse source material in multi-document summarization, as noted in the DiverseSumm benchmark (Huang et al., 2024). In this work, we contend that principled content selection is a simple way to increase source coverage on this task. As opposed to prompting an LLM to perform the summarization in a single step, we explicitly divide the task into three steps -- (1) reducing document collections to atomic key points, (2) using determinantal point processes (DPP) to perform select key points that prioritize diverse content, and (3) rewriting to the final summary. By combining prompting steps, for extraction and rewriting, with principled techniques, for content selection, we consistently improve source coverage on the DiverseSumm benchmark across various LLMs. Finally, we also show that by incorporating relevance to a provided user intent into the DPP kernel, we can generate personalized summaries that cover relevant source information while retaining coverage. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Query-focused Multi-document Summarization on DIVERSESUMM Relevance](): Query-focused Multi-document Summarization; DIVERSESUMM Relevance; Coverage: 69.72. - [Source Coverage Evaluation on DIVERSESUMM 1.0 (test)](): Source Coverage Evaluation; DIVERSESUMM 1.0 (test); Source Coverage: 59.23. - [Source Coverage Evaluation on DIVERSESUMM Augmented 1.0 (test)](): Source Coverage Evaluation; DIVERSESUMM Augmented 1.0 (test); Source Coverage: 0.5535. ## Original sources and implementation [Original paper]() [PDF]()