# Mix and Match: Context Pairing for Scalable Topic-Controlled Educational Summarisation

arXiv: https://arxiv.org/abs/2604.18087 · HTML: https://mlsanity.com/paper/2604.18087/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 21 references that are in the map.
- First posted on arXiv 20 Apr 2026.

## Builds on (most cited first, 12 of 12)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [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)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [CTRLsum: Towards Generic Controllable Text Summarization](https://mlsanity.com/paper/2012.04281/) (2020)
- [Controllable Neural Dialogue Summarization with Personal Named Entity Planning](https://mlsanity.com/paper/2109.13070/) (2021)
- [OASum: Large-Scale Open Domain Aspect-based Summarization](https://mlsanity.com/paper/2212.09233/) (2022)
- [Scalable Educational Question Generation with Pre-trained Language Models](https://mlsanity.com/paper/2305.07871/) (2023)
- [TrueLearn: A Family of Bayesian Algorithms to Match Lifelong Learners to Open Educational Resources](https://mlsanity.com/paper/1911.09471/) (2019)
- [A Novel Approach to Scalable and Automatic Topic-Controlled Question Generation in Education](https://mlsanity.com/paper/2501.05220/) (2025)
- [ExtraPhrase: Efficient Data Augmentation for Abstractive Summarization](https://mlsanity.com/paper/2201.05313/) (2022)

## Abstract (arXiv)

Topic-controlled summarisation enables users to generate summaries focused on specific aspects of source documents. This paper investigates a data augmentation strategy for training small language models (sLMs) to perform topic-controlled summarisation. We propose a pairwise data augmentation method that combines contexts from different documents to create contrastive training examples, enabling models to learn the relationship between topics and summaries more effectively. Using the SciTLDR dataset enriched with Wikipedia-derived topics, we systematically evaluate how augmentation scale affects model performance. Results show consistent improvements in win rate and semantic alignment as the augmentation scale increases, while the amount of real training data remains fixed. Consequently, a T5-base model trained with our augmentation approach achieves competitive performance relative to larger models, despite using significantly fewer parameters and substantially fewer real training examples.