# Controllable Abstraction in Summary Generation for Large Language Models via Prompt Engineering

arXiv: https://arxiv.org/abs/2510.15436 · HTML: https://mlsanity.com/paper/2510.15436/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 26 references that are in the map.
- First posted on arXiv 17 Oct 2025.

## Builds on (most cited first, 10 of 10)

- [Adapted Large Language Models Can Outperform Medical Experts in Clinical Text Summarization](https://mlsanity.com/paper/2309.07430/) (2023)
- [A Comprehensive Survey on Process-Oriented Automatic Text Summarization with Exploration of LLM-Based Methods](https://mlsanity.com/paper/2403.02901/) (2024)
- [FineSurE: Fine-grained Summarization Evaluation using LLMs](https://mlsanity.com/paper/2407.00908/) (2024)
- [TofuEval: Evaluating Hallucinations of LLMs on Topic-Focused Dialogue Summarization](https://mlsanity.com/paper/2402.13249/) (2024)
- [SummIt: Iterative Text Summarization via ChatGPT](https://mlsanity.com/paper/2305.14835/) (2023)
- [Automatic Text Summarization Methods: A Comprehensive Review](https://mlsanity.com/paper/2204.01849/) (2022)
- [Collaborative Multi-Agent Reinforcement Learning Approach for Elastic Cloud Resource Scaling](https://mlsanity.com/paper/2507.00550/) (2025)
- [Trustworthy Summarization via Uncertainty Quantification and Risk Awareness in Large Language Models](https://mlsanity.com/paper/2510.01231/) (2025)
- [Structured Memory Mechanisms for Stable Context Representation in Large Language Models](https://mlsanity.com/paper/2505.22921/) (2025)
- [Detecting Credit Card Fraud via Heterogeneous Graph Neural Networks with Graph Attention](https://mlsanity.com/paper/2504.08183/) (2025)

## Built on by (most cited first, 2 of 2)

- [Structural Priors and Modular Adapters in the Composable Fine-Tuning Algorithm of Large-Scale Models](https://mlsanity.com/paper/2511.03981/) (2025)
- [Dynamic Anomaly Identification in Accounting Transactions via Multi-Head Self-Attention Networks](https://mlsanity.com/paper/2511.12122/) (2025)

## Abstract (arXiv)

This study presents a controllable abstract summary generation method for large language models based on prompt engineering. To address the issues of summary quality and controllability in traditional methods, we design a multi-stage prompt generation framework. This framework generates summaries with varying levels of abstraction by performing semantic analysis, topic modeling, and noise control on the input text. The experiment uses the CNN/Daily Mail dataset and provides a detailed analysis of different prompt lengths, data noise, and text types. The experimental results show that prompt length has a significant impact on the quality of generated summaries. Both very short and very long prompt tokens result in a decrease in summary quality. Data noise also negatively affects the summary generation process. As noise levels increase, the ROUGE-L score gradually decreases. Furthermore, different text types have varying effects on the model's ability to generate summaries. The model performs best when handling news texts, while its performance is worse when processing academic articles. This research provides new insights into improving summary generation using large language models, particularly in how controlling prompt strategies and optimizing text preprocessing can enhance summary accuracy and controllability.