# CTRLsum: Towards Generic Controllable Text Summarization

arXiv: https://arxiv.org/abs/2012.04281 · HTML: https://mlsanity.com/paper/2012.04281/

## Key facts

- Cited by 98 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Dec 2020.

## Built on by (most cited first, 30 of 98)

- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP](https://mlsanity.com/paper/2103.00453/) (2021)
- [News Summarization and Evaluation in the Era of GPT-3](https://mlsanity.com/paper/2209.12356/) (2022)
- [Revisiting the Gold Standard: Grounding Summarization Evaluation with Robust Human Evaluation](https://mlsanity.com/paper/2212.07981/) (2022)
- [PEER: A Collaborative Language Model](https://mlsanity.com/paper/2208.11663/) (2022)
- [A Survey of GPT-3 Family Large Language Models Including ChatGPT and GPT-4](https://mlsanity.com/paper/2310.12321/) (2023)
- [Sparks: Inspiration for Science Writing using Language Models](https://mlsanity.com/paper/2110.07640/) (2021)
- [Element-aware Summarization with Large Language Models: Expert-aligned Evaluation and Chain-of-Thought Method](https://mlsanity.com/paper/2305.13412/) (2023)
- [Planning with Learned Entity Prompts for Abstractive Summarization](https://mlsanity.com/paper/2104.07606/) (2021)
- [An Empirical Survey on Long Document Summarization: Datasets, Models and Metrics](https://mlsanity.com/paper/2207.00939/) (2022)
- [From Sparse to Dense: GPT-4 Summarization with Chain of Density Prompting](https://mlsanity.com/paper/2309.04269/) (2023)
- [ChatGPT vs Human-authored Text: Insights into Controllable Text Summarization and Sentence Style Transfer](https://mlsanity.com/paper/2306.07799/) (2023)
- [Prompted Opinion Summarization with GPT-3.5](https://mlsanity.com/paper/2211.15914/) (2022)
- [ASPECTNEWS: Aspect-Oriented Summarization of News Documents](https://mlsanity.com/paper/2110.08296/) (2021)
- [Controllable Neural Dialogue Summarization with Personal Named Entity Planning](https://mlsanity.com/paper/2109.13070/) (2021)
- [Sequence Level Contrastive Learning for Text Summarization](https://mlsanity.com/paper/2109.03481/) (2021)
- [ChatGPT-powered Conversational Drug Editing Using Retrieval and Domain Feedback](https://mlsanity.com/paper/2305.18090/) (2023)
- [AdaPrompt: Adaptive Model Training for Prompt-based NLP](https://mlsanity.com/paper/2202.04824/) (2022)
- [PLANET: Dynamic Content Planning in Autoregressive Transformers for Long-form Text Generation](https://mlsanity.com/paper/2203.09100/) (2022)
- [A Well-Composed Text is Half Done! Composition Sampling for Diverse Conditional Generation](https://mlsanity.com/paper/2203.15108/) (2022)
- [Long-Span Summarization via Local Attention and Content Selection](https://mlsanity.com/paper/2105.03801/) (2021)
- [Generating Summaries with Controllable Readability Levels](https://mlsanity.com/paper/2310.10623/) (2023)
- [EntSUM: A Data Set for Entity-Centric Summarization](https://mlsanity.com/paper/2204.02213/) (2022)
- [Improving the Faithfulness of Abstractive Summarization via Entity Coverage Control](https://mlsanity.com/paper/2207.02263/) (2022)
- [Readability Controllable Biomedical Document Summarization](https://mlsanity.com/paper/2210.04705/) (2022)
- [Comparative Opinion Summarization via Collaborative Decoding](https://mlsanity.com/paper/2110.07520/) (2021)
- [Automatic Text Summarization Methods: A Comprehensive Review](https://mlsanity.com/paper/2204.01849/) (2022)
- [Socratic Pretraining: Question-Driven Pretraining for Controllable Summarization](https://mlsanity.com/paper/2212.10449/) (2022)
- [Referee: Reference-Free Sentence Summarization with Sharper Controllability through Symbolic Knowledge Distillation](https://mlsanity.com/paper/2210.13800/) (2022)
- [MACSum: Controllable Summarization with Mixed Attributes](https://mlsanity.com/paper/2211.05041/) (2022)

## Abstract (arXiv)

Current summarization systems yield generic summaries that are disconnected from users' preferences and expectations. To address this limitation, we present CTRLsum, a novel framework for controllable summarization. Our approach enables users to control multiple aspects of generated summaries by interacting with the summarization system through textual input in the form of a set of keywords or descriptive prompts. Using a single unified model, CTRLsum is able to achieve a broad scope of summary manipulation at inference time without requiring additional human annotations or pre-defining a set of control aspects during training. We quantitatively demonstrate the effectiveness of our approach on three domains of summarization datasets and five control aspects: 1) entity-centric and 2) length-controllable summarization, 3) contribution summarization on scientific papers, 4) invention purpose summarization on patent filings, and 5) question-guided summarization on news articles in a reading comprehension setting. Moreover, when used in a standard, uncontrolled summarization setting, CTRLsum achieves state-of-the-art results on the CNN/DailyMail dataset. Code and model checkpoints are available at https://github.com/salesforce/ctrl-sum