MODS: Moderating a Mixture of Document Speakers to Summarize Debatable Queries in Document Collections

TL;DR

This paper introduces MODS, a multi-LLM framework that generates balanced, comprehensive summaries for debatable queries by mimicking human panel discussions, addressing limitations of previous query-focused summarization methods.

Contribution

MODS is a novel multi-LLM approach that models document summarization as a moderated discussion, improving coverage and balance in debatable query summaries.

Findings

MODS outperforms SOTA by 38-59% in coverage and balance metrics.

MODS produces more balanced and readable summaries according to user evaluations.

Experiments on ConflictingQA and DebateQFS datasets demonstrate effectiveness.

Abstract

Query-focused summarization (QFS) gives a summary of documents to answer a query. Past QFS work assumes queries have one answer, ignoring debatable ones (Is law school worth it?). We introduce Debatable QFS (DQFS), a task to create summaries that answer debatable queries via documents with opposing perspectives; summaries must comprehensively cover all sources and balance perspectives, favoring no side. These goals elude LLM QFS systems, which: 1) lack structured content plans, failing to guide LLMs to write balanced summaries, and 2) use the same query to retrieve contexts across documents, failing to cover all perspectives specific to each document's content. To overcome this, we design MODS, a multi-LLM framework mirroring human panel discussions. MODS treats documents as individual Speaker LLMs and has a Moderator LLM that picks speakers to respond to tailored queries for planned topics. Speakers use tailored queries to retrieve relevant contexts from their documents and supply perspectives, which are tracked in a rich outline, yielding a content plan to guide the final summary. Experiments on ConflictingQA with controversial web queries and DebateQFS, our new dataset of debate queries from Debatepedia, show MODS beats SOTA by 38-59% in topic paragraph coverage and balance, based on new citation metrics. Users also find MODS's summaries to be readable and more balanced.