# Controllable Text Generation with Focused Variation

arXiv: https://arxiv.org/abs/2009.12046 · HTML: https://mlsanity.com/paper/2009.12046/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Sep 2020.

## Built on by (most cited first, 7 of 7)

- [JailbreakZoo: Survey, Landscapes, and Horizons in Jailbreaking Large Language and Vision-Language Models](https://mlsanity.com/paper/2407.01599/) (2024)
- [Controllable Semantic Parsing via Retrieval Augmentation](https://mlsanity.com/paper/2110.08458/) (2021)
- [Disentangling Generative Factors in Natural Language with Discrete Variational Autoencoders](https://mlsanity.com/paper/2109.07169/) (2021)
- [COFFEE: Counterfactual Fairness for Personalized Text Generation in Explainable Recommendation](https://mlsanity.com/paper/2210.15500/) (2022)
- [POSGen: Personalized Opening Sentence Generation for Online Insurance Sales](https://mlsanity.com/paper/2302.06470/) (2023)
- [The Interpretability of Codebooks in Model-Based Reinforcement Learning is Limited](https://mlsanity.com/paper/2407.19532/) (2024)
- [Usage-Modulated Sentiment Representations in Large Language Models](https://mlsanity.com/paper/2610.05069/) (2026)

## Abstract (arXiv)

This work introduces Focused-Variation Network (FVN), a novel model to control language generation. The main problems in previous controlled language generation models range from the difficulty of generating text according to the given attributes, to the lack of diversity of the generated texts. FVN addresses these issues by learning disjoint discrete latent spaces for each attribute inside codebooks, which allows for both controllability and diversity, while at the same time generating fluent text. We evaluate FVN on two text generation datasets with annotated content and style, and show state-of-the-art performance as assessed by automatic and human evaluations.