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

arXiv: https://arxiv.org/abs/2604.10687 · HTML: https://mlsanity.com/paper/2604.10687/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 38 references that are in the map.
- First posted on arXiv 12 Apr 2026.

## Builds on (most cited first, 23 of 23)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [Gemma: Open Models Based on Gemini Research and Technology](https://mlsanity.com/paper/2403.08295/) (2024)
- [SummEval: Re-evaluating Summarization Evaluation](https://mlsanity.com/paper/2007.12626/) (2020)
- [A Neural Attention Model for Abstractive Sentence Summarization](https://mlsanity.com/paper/1509.00685/) (2015)
- [Asking and Answering Questions to Evaluate the Factual Consistency of Summaries](https://mlsanity.com/paper/2004.04228/) (2020)
- [QuestEval: Summarization Asks for Fact-based Evaluation](https://mlsanity.com/paper/2103.12693/) (2021)
- [Break It Down: A Question Understanding Benchmark](https://mlsanity.com/paper/2001.11770/) (2020)
- [MOCHA: A Dataset for Training and Evaluating Generative Reading Comprehension Metrics](https://mlsanity.com/paper/2010.03636/) (2020)
- [ChatGPT MT: Competitive for High- (but not Low-) Resource Languages](https://mlsanity.com/paper/2309.07423/) (2023)
- [RQUGE: Reference-Free Metric for Evaluating Question Generation by Answering the Question](https://mlsanity.com/paper/2211.01482/) (2022)
- [Sequence to sequence pretraining for a less-resourced Slovenian language](https://mlsanity.com/paper/2207.13988/) (2022)
- [Generative Model for Less-Resourced Language with 1 billion parameters](https://mlsanity.com/paper/2410.06898/) (2024)
- [Cross-lingual Transfer of Abstractive Summarizer to Less-resource Language](https://mlsanity.com/paper/2012.04307/) (2020)
- [Named Entity Inclusion in Abstractive Text Summarization](https://mlsanity.com/paper/2307.02570/) (2023)
- [Learning to Rank Salient Content for Query-focused Summarization](https://mlsanity.com/paper/2411.00324/) (2024)
- [Combination of abstractive and extractive approaches for summarization of long scientific texts](https://mlsanity.com/paper/2006.05354/) (2020)
- [One model to rule them all: ranking Slovene summarizers](https://mlsanity.com/paper/2306.11518/) (2023)

## Abstract (arXiv)

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.