QFS-Composer: Query-focused summarization pipeline for less resourced languages

arXiv cs.CL / 4/14/2026

📰 NewsSignals & Early TrendsIdeas & Deep AnalysisModels & Research

共有:

Key Points

LLMs perform well at summarization, but their quality declines sharply for less-resourced languages with limited labeled data and evaluation tooling.
The paper introduces QFS-Composer, a query-focused summarization pipeline that combines query decomposition, question generation, question answering, and abstractive summarization to better align summaries with user intent.
To support supervision and evaluation in a low-resource setting, the authors build Slovenian QA and QG models derived from a Slovene LLM and adapt reference-free evaluation methods for summary quality.
Experiments on Slovenian show that the QA-guided pipeline improves consistency and relevance compared with baseline LLM summarization approaches.
The work proposes an extensible methodology aimed at advancing query-focused summarization in additional less-resourced languages beyond Slovenian.

Abstract

Large language models (LLMs) demonstrate strong performance in text summarization, yet their effectiveness drops significantly across languages with restricted training resources. This work addresses the challenge of query-focused summarization (QFS) in less-resourced languages, where labeled datasets and evaluation tools are limited. We present a novel QFS framework, QFS-Composer, that integrates query decomposition, question generation (QG), question answering (QA), and abstractive summarization to improve the factual alignment of a summary with user intent. We test our approach on the Slovenian language. To enable high-quality supervision and evaluation, we develop the Slovenian QA and QG models based on a Slovene LLM and adapt evaluation approaches for reference-free summary evaluation. Empirical evaluation shows that the QA-guided summarization pipeline yields improved consistency and relevance over baseline LLMs. Our work establishes an extensible methodology for advancing QFS in less-resourced languages.