QFS-Composer: Query-focused summarization pipeline for less resourced languages
For developers of NLP systems in less-resourced languages, this work provides a methodology to improve query-focused summarization where labeled data is scarce.
The paper tackles query-focused summarization in less-resourced languages, proposing QFS-Composer that integrates query decomposition, question generation, question answering, and abstractive summarization. On Slovenian, the pipeline improves consistency and relevance over baseline LLMs.
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.