# Improved Paraphrase Generation via Controllable Latent Diffusion

arXiv: https://arxiv.org/abs/2404.08938 · HTML: https://mlsanity.com/paper/2404.08938/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Discrete and text diffusion, one of 14 directions in Diffusion models.
- Builds on 3 of its 5 references that are in the map.
- First posted on arXiv 13 Apr 2024.

## Placed in

- Diffusion models / [Discrete and text diffusion](https://mlsanity.com/diffusion/discrete-and-text-diffusion/)

## Builds on (most cited first, 3 of 3)

- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [On the Evaluation Metrics for Paraphrase Generation](https://mlsanity.com/paper/2202.08479/) (2022)
- [Improving Large-scale Paraphrase Acquisition and Generation](https://mlsanity.com/paper/2210.03235/) (2022)

## Built on by (most cited first, 1 of 1)

- [A Survey on Diffusion Language Models](https://mlsanity.com/paper/2508.10875/) (2025)

## Abstract (arXiv)

Paraphrase generation strives to generate high-quality and diverse expressions of a given text, a domain where diffusion models excel. Though SOTA diffusion generation reconciles generation quality and diversity, textual diffusion suffers from a truncation issue that hinders efficiency and quality control. In this work, we propose textitLatent textitDiffusion textitParaphraser~(LDP), a novel paraphrase generation by modeling a controllable diffusion process given a learned latent space. LDP achieves superior generation efficiency compared to its diffusion counterparts. It can facilitate only input segments to ensure paraphrase semantics, improving the results without external features. Experiments show that LDP better reconciles paraphrase generation quality and diversity than baselines. Further analysis shows that our method is also helpful to other similar text generations and domain adaptations