# Diversity Augmentation of Dynamic User Preference Data for Boosting Personalized Text Summarizers

arXiv: https://arxiv.org/abs/2510.10082 · HTML: https://mlsanity.com/paper/2510.10082/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 51 references that are in the map.
- First posted on arXiv 11 Oct 2025.

## Builds on (most cited first, 30 of 31)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Teaching Machines to Read and Comprehend](https://mlsanity.com/paper/1506.03340/) (2015)
- [Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model](https://mlsanity.com/paper/1906.01749/) (2019)
- [A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications](https://mlsanity.com/paper/2402.07927/) (2024)
- [GSum: A General Framework for Guided Neural Abstractive Summarization](https://mlsanity.com/paper/2010.08014/) (2020)
- [CTRLsum: Towards Generic Controllable Text Summarization](https://mlsanity.com/paper/2012.04281/) (2020)
- [Boosting Language Models Reasoning with Chain-of-Knowledge Prompting](https://mlsanity.com/paper/2306.06427/) (2023)
- [Neural News Recommendation with Attentive Multi-View Learning](https://mlsanity.com/paper/1907.05576/) (2019)
- [Improving Zero and Few-Shot Abstractive Summarization with Intermediate Fine-tuning and Data Augmentation](https://mlsanity.com/paper/2010.12836/) (2020)
- [Learning Data Manipulation for Augmentation and Weighting](https://mlsanity.com/paper/1910.12795/) (2019)
- [Augmenting Sequential Recommendation with Pseudo-Prior Items via Reversely Pre-training Transformer](https://mlsanity.com/paper/2105.00522/) (2021)
- [Dataset Regeneration for Sequential Recommendation](https://mlsanity.com/paper/2405.17795/) (2024)
- [Improving Recommendation Fairness via Data Augmentation](https://mlsanity.com/paper/2302.06333/) (2023)
- [Prompt Chaining or Stepwise Prompt? Refinement in Text Summarization](https://mlsanity.com/paper/2406.00507/) (2024)
- [A Self-Correcting Sequential Recommender](https://mlsanity.com/paper/2303.02297/) (2023)
- [Improving the Robustness of Summarization Systems with Dual Augmentation](https://mlsanity.com/paper/2306.01090/) (2023)
- [Structured Chain-of-Thought Prompting for Few-Shot Generation of Content-Grounded QA Conversations](https://mlsanity.com/paper/2402.11770/) (2024)
- [Tell me what I need to know: Exploring LLM-based (Personalized) Abstractive Multi-Source Meeting Summarization](https://mlsanity.com/paper/2410.14545/) (2024)
- [What Makes a Good and Useful Summary? Incorporating Users in Automatic Summarization Research](https://mlsanity.com/paper/2012.07619/) (2020)
- [Masked and Swapped Sequence Modeling for Next Novel Basket Recommendation in Grocery Shopping](https://mlsanity.com/paper/2308.01308/) (2023)
- [A Guide To Effectively Leveraging LLMs for Low-Resource Text Summarization: Data Augmentation and Semi-supervised Approaches](https://mlsanity.com/paper/2407.07341/) (2024)
- [Segment, Shuffle, and Stitch: A Simple Layer for Improving Time-Series Representations](https://mlsanity.com/paper/2405.20082/) (2024)
- [Personalized Abstractive Summarization by Tri-agent Generation Pipeline](https://mlsanity.com/paper/2305.02483/) (2023)
- [Panoramic Interests: Stylistic-Content Aware Personalized Headline Generation](https://mlsanity.com/paper/2501.11900/) (2025)
- [PerSEval: Assessing Personalization in Text Summarizers](https://mlsanity.com/paper/2407.00453/) (2024)
- [Learning to Augment for Casual User Recommendation](https://mlsanity.com/paper/2204.00926/) (2022)
- [Fact-Preserved Personalized News Headline Generation](https://mlsanity.com/paper/2501.11828/) (2025)

## Abstract (arXiv)

Document summarization enables efficient extraction of user-relevant content but is inherently shaped by individual subjectivity, making it challenging to identify subjective salient information in multifaceted documents. This complexity underscores the necessity for personalized summarization. However, training models for personalized summarization has so far been challenging, particularly because diverse training data containing both user preference history (i.e., click-skip trajectory) and expected (gold-reference) summaries are scarce. The MS/CAS PENS dataset is a valuable resource but includes only preference history without target summaries, preventing end-to-end supervised learning, and its limited topic-transition diversity further restricts generalization. To address this, we propose PerAugy, a novel cross-trajectory shuffling and summary-content perturbation based data augmentation technique that significantly boosts the accuracy of four state-of-the-art baseline (SOTA) user-encoders commonly used in personalized summarization frameworks (best result: 0.132uparrow w.r.t AUC). We select two such SOTA summarizer frameworks as baselines and observe that when augmented with their corresponding improved user-encoders, they consistently show an increase in personalization (avg. boost: 61.2%uparrow w.r.t. PSE-SU4 metric). As a post-hoc analysis of the role of induced diversity in the augmented dataset by peraugy, we introduce three dataset diversity metrics -- TP, RTC, and degreed to quantify the induced diversity. We find that TP and DegreeD strongly correlate with user-encoder performance on the PerAugy-generated dataset across all accuracy metrics, indicating that increased dataset diversity is a key factor driving performance gains.