# MACSum: Controllable Summarization with Mixed Attributes

arXiv: https://arxiv.org/abs/2211.05041 · HTML: https://mlsanity.com/paper/2211.05041/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 60 references that are in the map.
- First posted on arXiv 9 Nov 2022.

## Builds on (most cited first, 30 of 35)

- [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)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [Teaching Machines to Read and Comprehend](https://mlsanity.com/paper/1506.03340/) (2015)
- [GPT Understands, Too](https://mlsanity.com/paper/2103.10385/) (2021)
- [It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners](https://mlsanity.com/paper/2009.07118/) (2020)
- [A Neural Attention Model for Abstractive Sentence Summarization](https://mlsanity.com/paper/1509.00685/) (2015)
- [Learning How to Ask: Querying LMs with Mixtures of Soft Prompts](https://mlsanity.com/paper/2104.06599/) (2021)
- [A Deep Reinforced Model for Abstractive Summarization](https://mlsanity.com/paper/1705.04304/) (2017)
- [QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization](https://mlsanity.com/paper/2104.05938/) (2021)
- [News Summarization and Evaluation in the Era of GPT-3](https://mlsanity.com/paper/2209.12356/) (2022)
- [AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts](https://mlsanity.com/paper/2010.15980/) (2020)
- [Noisy Channel Language Model Prompting for Few-Shot Text Classification](https://mlsanity.com/paper/2108.04106/) (2021)
- [GSum: A General Framework for Guided Neural Abstractive Summarization](https://mlsanity.com/paper/2010.08014/) (2020)
- [Neural Summarization by Extracting Sentences and Words](https://mlsanity.com/paper/1603.07252/) (2016)
- [Controllable Abstractive Summarization](https://mlsanity.com/paper/1711.05217/) (2017)
- [CTRLsum: Towards Generic Controllable Text Summarization](https://mlsanity.com/paper/2012.04281/) (2020)
- [Better Rewards Yield Better Summaries: Learning to Summarise Without References](https://mlsanity.com/paper/1909.01214/) (2019)
- [Planning with Learned Entity Prompts for Abstractive Summarization](https://mlsanity.com/paper/2104.07606/) (2021)
- [Aspect-Controllable Opinion Summarization](https://mlsanity.com/paper/2109.03171/) (2021)
- [AdaPrompt: Adaptive Model Training for Prompt-based NLP](https://mlsanity.com/paper/2202.04824/) (2022)
- [Z-Code++: A Pre-trained Language Model Optimized for Abstractive Summarization](https://mlsanity.com/paper/2208.09770/) (2022)
- [Summarizing Text on Any Aspects: A Knowledge-Informed Weakly-Supervised Approach](https://mlsanity.com/paper/2010.06792/) (2020)
- [EntSUM: A Data Set for Entity-Centric Summarization](https://mlsanity.com/paper/2204.02213/) (2022)
- [Control, Generate, Augment: A Scalable Framework for Multi-Attribute Text Generation](https://mlsanity.com/paper/2004.14983/) (2020)

## Built on by (most cited first, 13 of 13)

- [Adaptable Logical Control for Large Language Models](https://mlsanity.com/paper/2406.13892/) (2024)
- [Generating Summaries with Controllable Readability Levels](https://mlsanity.com/paper/2310.10623/) (2023)
- [Fair Abstractive Summarization of Diverse Perspectives](https://mlsanity.com/paper/2311.07884/) (2023)
- [UniSumm and SummZoo: Unified Model and Diverse Benchmark for Few-Shot Summarization](https://mlsanity.com/paper/2211.09783/) (2022)
- [Investigating Table-to-Text Generation Capabilities of LLMs in Real-World Information Seeking Scenarios](https://mlsanity.com/paper/2305.14987/) (2023)
- [Toward Unified Controllable Text Generation via Regular Expression Instruction](https://mlsanity.com/paper/2309.10447/) (2023)
- [PersonalSum: A User-Subjective Guided Personalized Summarization Dataset for Large Language Models](https://mlsanity.com/paper/2410.03905/) (2024)
- [GenerationPrograms: Fine-grained Attribution with Executable Programs](https://mlsanity.com/paper/2506.14580/) (2025)
- [Dialogue Agents 101: A Beginner's Guide to Critical Ingredients for Designing Effective Conversational Systems](https://mlsanity.com/paper/2307.07255/) (2023)
- [Introducing Spotlight: A Novel Approach for Generating Captivating Key Information from Documents](https://mlsanity.com/paper/2509.10935/) (2025)
- [SWIM: Student Writing Simulation via Proficiency-Conditioned Generation](https://mlsanity.com/paper/2609.03215/) (2026)
- [CCSBench: Evaluating Compositional Controllability in LLMs for Scientific Document Summarization](https://mlsanity.com/paper/2410.12601/) (2024)
- [MAPLE: Medical Aspect-Based Summarization with Phrase-Level Evidence](https://mlsanity.com/paper/2601.03418/) (2026)

## Abstract (arXiv)

Controllable summarization allows users to generate customized summaries with specified attributes. However, due to the lack of designated annotations of controlled summaries, existing works have to craft pseudo datasets by adapting generic summarization benchmarks. Furthermore, most research focuses on controlling single attributes individually (e.g., a short summary or a highly abstractive summary) rather than controlling a mix of attributes together (e.g., a short and highly abstractive summary). In this paper, we propose MACSum, the first human-annotated summarization dataset for controlling mixed attributes. It contains source texts from two domains, news articles and dialogues, with human-annotated summaries controlled by five designed attributes (Length, Extractiveness, Specificity, Topic, and Speaker). We propose two simple and effective parameter-efficient approaches for the new task of mixed controllable summarization based on hard prompt tuning and soft prefix tuning. Results and analysis demonstrate that hard prompt models yield the best performance on all metrics and human evaluations. However, mixed-attribute control is still challenging for summarization tasks. Our dataset and code are available at https://github.com/psunlpgroup/MACSum.