# LAMPAT: Low-Rank Adaption for Multilingual Paraphrasing Using Adversarial Training

arXiv: https://arxiv.org/abs/2401.04348 · HTML: https://mlsanity.com/paper/2401.04348/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 29 references that are in the map.
- First posted on arXiv 9 Jan 2024.

## Builds on (most cited first, 21 of 21)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (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)
- [Cross-lingual Language Model Pretraining](https://mlsanity.com/paper/1901.07291/) (2019)
- [Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning](https://mlsanity.com/paper/1704.03976/) (2017)
- [Adversarial Training for Free!](https://mlsanity.com/paper/1904.12843/) (2019)
- [You Only Propagate Once: Accelerating Adversarial Training via Maximal Principle](https://mlsanity.com/paper/1905.00877/) (2019)
- [Pre-training via Paraphrasing](https://mlsanity.com/paper/2006.15020/) (2020)
- [Understanding Catastrophic Forgetting and Remembering in Continual Learning with Optimal Relevance Mapping](https://mlsanity.com/paper/2102.11343/) (2021)
- [On the Evaluation Metrics for Paraphrase Generation](https://mlsanity.com/paper/2202.08479/) (2022)
- [Novelty Controlled Paraphrase Generation with Retrieval Augmented Conditional Prompt Tuning](https://mlsanity.com/paper/2202.00535/) (2022)
- [Open Subtitles Paraphrase Corpus for Six Languages](https://mlsanity.com/paper/1809.06142/) (2018)
- [Factorising Meaning and Form for Intent-Preserving Paraphrasing](https://mlsanity.com/paper/2105.15053/) (2021)
- [Joint Copying and Restricted Generation for Paraphrase](https://mlsanity.com/paper/1611.09235/) (2016)
- [Human-Paraphrased References Improve Neural Machine Translation](https://mlsanity.com/paper/2010.10245/) (2020)
- [Unsupervised Paraphrasing with Pretrained Language Models](https://mlsanity.com/paper/2010.12885/) (2020)
- [Adversarial Training for Commonsense Inference](https://mlsanity.com/paper/2005.08156/) (2020)
- [Zero-Shot Paraphrase Generation with Multilingual Language Models](https://mlsanity.com/paper/1911.03597/) (2019)

## Built on by (most cited first, 8 of 8)

- [Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontiers](https://mlsanity.com/paper/2404.04925/) (2024)
- [Low-Rank Adaptation for Foundation Models: A Comprehensive Review](https://mlsanity.com/paper/2501.00365/) (2024)
- [Multilingual Text-to-SQL: Benchmarking the Limits of Language Models with Collaborative Language Agents](https://mlsanity.com/paper/2509.24405/) (2025)
- [UniBridge: A Unified Approach to Cross-Lingual Transfer Learning for Low-Resource Languages](https://mlsanity.com/paper/2406.09717/) (2024)
- [An Efficient and Effective Evaluator for Text2SQL Models on Unseen and Unlabeled Data](https://mlsanity.com/paper/2603.07841/) (2026)
- [Learning to Evaluate: Cost-Effective Model Evaluation on Unlabeled Data with Meta-Learning](https://mlsanity.com/paper/2605.23595/) (2026)
- [UniBERT: Adversarial Training for Language-Universal Representations](https://mlsanity.com/paper/2503.12608/) (2025)
- [An Efficient and Effective Agentic Group Shilling Attack on Recommender Systems](https://mlsanity.com/paper/2609.09551/) (2026)

## Abstract (arXiv)

Paraphrases are texts that convey the same meaning while using different words or sentence structures. It can be used as an automatic data augmentation tool for many Natural Language Processing tasks, especially when dealing with low-resource languages, where data shortage is a significant problem. To generate a paraphrase in multilingual settings, previous studies have leveraged the knowledge from the machine translation field, i.e., forming a paraphrase through zero-shot machine translation in the same language. Despite good performance on human evaluation, those methods still require parallel translation datasets, thus making them inapplicable to languages that do not have parallel corpora. To mitigate that problem, we proposed the first unsupervised multilingual paraphrasing model, LAMPAT (Low-rank Adaptation for Multilingual Paraphrasing using Adversarial Training), by which monolingual dataset is sufficient enough to generate a human-like and diverse sentence. Throughout the experiments, we found out that our method not only works well for English but can generalize on unseen languages as well. Data and code are available at https://github.com/VinAIResearch/LAMPAT.