# Hooks in the Headline: Learning to Generate Headlines with Controlled Styles

arXiv: https://arxiv.org/abs/2004.01980 · HTML: https://mlsanity.com/paper/2004.01980/

## Key facts

- Cited by 46 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Apr 2020.

## Built on by (most cited first, 30 of 46)

- [Challenges and Strategies in Cross-Cultural NLP](https://mlsanity.com/paper/2203.10020/) (2022)
- [Pretrained Language Models for Text Generation: A Survey](https://mlsanity.com/paper/2201.05273/) (2022)
- [Style Vectors for Steering Generative Large Language Model](https://mlsanity.com/paper/2402.01618/) (2024)
- [StylePTB: A Compositional Benchmark for Fine-grained Controllable Text Style Transfer](https://mlsanity.com/paper/2104.05196/) (2021)
- [Multitasking Framework for Unsupervised Simple Definition Generation](https://mlsanity.com/paper/2203.12926/) (2022)
- [Controllable Text Summarization: Unraveling Challenges, Approaches, and Prospects -- A Survey](https://mlsanity.com/paper/2311.09212/) (2023)
- [Prompt-Based Editing for Text Style Transfer](https://mlsanity.com/paper/2301.11997/) (2023)
- [A Call for Standardization and Validation of Text Style Transfer Evaluation](https://mlsanity.com/paper/2306.00539/) (2023)
- [Inference Time Style Control for Summarization](https://mlsanity.com/paper/2104.01724/) (2021)
- [Large Scale Multi-Lingual Multi-Modal Summarization Dataset](https://mlsanity.com/paper/2302.06560/) (2023)
- [Tweetorial Hooks: Generative AI Tools to Motivate Science on Social Media](https://mlsanity.com/paper/2305.12265/) (2023)
- [Evaluating Generative Ad Hoc Information Retrieval](https://mlsanity.com/paper/2311.04694/) (2023)
- [Authorship Style Transfer with Policy Optimization](https://mlsanity.com/paper/2403.08043/) (2024)
- [News Headline Grouping as a Challenging NLU Task](https://mlsanity.com/paper/2105.05391/) (2021)
- [Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models](https://mlsanity.com/paper/2305.12544/) (2023)
- [Evaluating the Smooth Control of Attribute Intensity in Text Generation with LLMs](https://mlsanity.com/paper/2406.04460/) (2024)
- [Audience-Centric Natural Language Generation via Style Infusion](https://mlsanity.com/paper/2301.10283/) (2023)
- [Stylized Knowledge-Grounded Dialogue Generation via Disentangled Template Rewriting](https://mlsanity.com/paper/2204.05610/) (2022)
- [StyleFlow: Disentangle Latent Representations via Normalizing Flow for Unsupervised Text Style Transfer](https://mlsanity.com/paper/2212.09670/) (2022)
- [Meta-Tuning LLMs to Leverage Lexical Knowledge for Generalizable Language Style Understanding](https://mlsanity.com/paper/2305.14592/) (2023)
- [Style Transfer with Multi-iteration Preference Optimization](https://mlsanity.com/paper/2406.11581/) (2024)
- [Panoramic Interests: Stylistic-Content Aware Personalized Headline Generation](https://mlsanity.com/paper/2501.11900/) (2025)
- [The Effectiveness of Style Vectors for Steering Large Language Models: A Human Evaluation](https://mlsanity.com/paper/2601.21505/) (2026)
- [Towards Zero and Few-shot Knowledge-seeking Turn Detection in Task-orientated Dialogue Systems](https://mlsanity.com/paper/2109.08820/) (2021)
- [Noisy Pairing and Partial Supervision for Stylized Opinion Summarization](https://mlsanity.com/paper/2211.08723/) (2022)
- [HonestBait: Forward References for Attractive but Faithful Headline Generation](https://mlsanity.com/paper/2306.14828/) (2023)
- [Exploiting Social Media Content for Self-Supervised Style Transfer](https://mlsanity.com/paper/2205.08814/) (2022)
- [Contrastive Learning enhanced Author-Style Headline Generation](https://mlsanity.com/paper/2211.03305/) (2022)
- [How to Generate Popular Post Headlines on Social Media?](https://mlsanity.com/paper/2309.09949/) (2023)
- [Specializing Small Language Models towards Complex Style Transfer via Latent Attribute Pre-Training](https://mlsanity.com/paper/2309.10929/) (2023)

## Abstract (arXiv)

Current summarization systems only produce plain, factual headlines, but do not meet the practical needs of creating memorable titles to increase exposure. We propose a new task, Stylistic Headline Generation (SHG), to enrich the headlines with three style options (humor, romance and clickbait), in order to attract more readers. With no style-specific article-headline pair (only a standard headline summarization dataset and mono-style corpora), our method TitleStylist generates style-specific headlines by combining the summarization and reconstruction tasks into a multitasking framework. We also introduced a novel parameter sharing scheme to further disentangle the style from the text. Through both automatic and human evaluation, we demonstrate that TitleStylist can generate relevant, fluent headlines with three target styles: humor, romance, and clickbait. The attraction score of our model generated headlines surpasses that of the state-of-the-art summarization model by 9.68%, and even outperforms human-written references.