mlsanityData to 7 Oct 2026

Novelty Controlled Paraphrase Generation with Retrieval Augmented Conditional Prompt Tuning

arXiv 2202.00535 ↗First posted 1 Feb 2022cs.CL cs.AIcited by 25

On the map: Retrieval-augmented generation → Generation and context integration

Abstract (arXiv)

Paraphrase generation is a fundamental and long-standing task in natural language processing. In this paper, we concentrate on two contributions to the task: (1) we propose Retrieval Augmented Prompt Tuning (RAPT) as a parameter-efficient method to adapt large pre-trained language models for paraphrase generation; (2) we propose Novelty Conditioned RAPT (NC-RAPT) as a simple model-agnostic method of using specialized prompt tokens for controlled paraphrase generation with varying levels of lexical novelty. By conducting extensive experiments on four datasets, we demonstrate the effectiveness of the proposed approaches for retaining the semantic content of the original text while inducing lexical novelty in the generation.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation. Builds on 36 of its 57 references that are in the map. First posted on arXiv 1 Feb 2022.

Builds on

36 of 57 references.

References · 36

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  5. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  6. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  7. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  8. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  9. 2019Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelismcited by 1,829
  10. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,255
  11. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,184
  12. 2019How Can We Know What Language Models Know?cited by 953
24 more
  1. 2020Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inferencecited by 934
  2. 2021GPT Understands, Toocited by 715
  3. 2020It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learnerscited by 668
  4. 2018Adversarial Example Generation with Syntactically Controlled Paraphrase Networkscited by 282
  5. 2018A Retrieve-and-Edit Framework for Predicting Structured Outputscited by 73
  6. 2017Paraphrase Generation with Deep Reinforcement Learningcited by 58
  7. 2020Neural Syntactic Preordering for Controlled Paraphrase Generationcited by 56
  8. 2017A Deep Generative Framework for Paraphrase Generationcited by 54
  9. 2016Neural Paraphrase Generation with Stacked Residual LSTM Networkscited by 52
  10. 2020Syntax-guided Controlled Generation of Paraphrasescited by 47
  11. 2021Generating Syntactically Controlled Paraphrases without Using Annotated Parallel Pairscited by 45
  12. 2019Controllable Paraphrase Generation with a Syntactic Exemplarcited by 44
  13. 2019Unsupervised Paraphrasing by Simulated Annealingcited by 37
  14. 2019Paraphrasing with Large Language Modelscited by 35
  15. 2019Decomposable Neural Paraphrase Generationcited by 30
  16. 2018Integrating Transformer and Paraphrase Rules for Sentence Simplificationcited by 29
  17. 2021ParaSCI: A Large Scientific Paraphrase Dataset for Longer Paraphrase Generationcited by 28
  18. 2020Paraphrase Generation with Latent Bag of Wordscited by 27
  19. 2021Factorising Meaning and Form for Intent-Preserving Paraphrasingcited by 22
  20. 2016Joint Copying and Restricted Generation for Paraphrasecited by 17
  21. 2019An Empirical Comparison on Imitation Learning and Reinforcement Learning for Paraphrase Generationcited by 11
  22. 2020Reflective Decoding: Beyond Unidirectional Generation with Off-the-Shelf Language Modelscited by 9
  23. 2021Pushing Paraphrase Away from Original Sentence: A Multi-Round Paraphrase Generation Approachcited by 7
  24. 2019Polly Want a Cracker: Analyzing Performance of Parroting on Paraphrase Generation Datasetscited by 2

Built on by

Cited by year

Citing papers per year: 2022: 5; 2023: 8; 2024: 12.

25 papers.

Sort:

By area:

  1. 2022Repair Is Nearly Generation: Multilingual Program Repair with LLMscited by 68
  2. 2023CoEdIT: Text Editing by Task-Specific Instruction Tuningcited by 67
  3. 2023Building Emotional Support Chatbots in the Era of LLMscited by 62
  4. 2023ChatGPT to Replace Crowdsourcing of Paraphrases for Intent Classification: Higher Diversity and Comparable Model Robustnesscited by 41
  5. 2023Continual Vision-Language Representation Learning with Off-Diagonal Informationcited by 40
  6. 2022Measuring Reliability of Large Language Models through Semantic Consistencycited by 38
  7. 2023Large AI Model-Based Semantic Communicationscited by 35
  8. 2022Cross-Lingual Retrieval Augmented Prompt for Low-Resource Languagescited by 17
  9. 2023From Classification to Generation: Insights into Crosslingual Retrieval Augmented ICLcited by 17
  10. 2024Effects of diversity incentives on sample diversity and downstream model performance in LLM-based text augmentationcited by 17
  11. 2024mEdIT: Multilingual Text Editing via Instruction Tuningcited by 13
  12. 2023ParaAMR: A Large-Scale Syntactically Diverse Paraphrase Dataset by AMR Back-Translationcited by 11
13 more
  1. 2024Improving Tool Retrieval by Leveraging Large Language Models for Query Generationcited by 11
  2. 2024Monotonic Paraphrasing Improves Generalization of Language Model Promptingcited by 10
  3. 2022What Makes Data-to-Text Generation Hard for Pretrained Language Models?cited by 8
  4. 2024LAMPAT: Low-Rank Adaption for Multilingual Paraphrasing Using Adversarial Trainingcited by 8
  5. 2024LLMs vs Established Text Augmentation Techniques for Classification: When do the Benefits Outweight the Costs?cited by 8
  6. 2022Unsupervised Syntactically Controlled Paraphrase Generation with Abstract Meaning Representationscited by 4
  7. 2023MixPro: Simple yet Effective Data Augmentation for Prompt-based Learningcited by 4
  8. 2024Spivavtor: An Instruction Tuned Ukrainian Text Editing Modelcited by 4
  9. 2024Patent-CR: A Dataset for Patent Claim Revisioncited by 4
  10. 2024Parameter Efficient Diverse Paraphrase Generation Using Sequence-Level Knowledge Distillationcited by 3
  11. 2024Learning to Adapt to Low-Resource Paraphrase Generationcited by 2
  12. 2024Task-Oriented Paraphrase Analyticscited by 1
  13. 2024Plug and Play with Prompts: A Prompt Tuning Approach for Controlling Text Generationcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2024Improved Paraphrase Generation via Controllable Latent Diffusion
  2. 2024Towards Human Understanding of Paraphrase Types in Large Language Models
  3. 2025Zero-Shot Keyphrase Generation: Investigating Specialized Instructions and Multi-Sample Aggregation on Large Language Models
  4. 2025The Devil is in the Prompts: Retrieval-Augmented Prompt Optimization for Text-to-Video Generation
  5. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
  6. 2022Retrieval-Augmented Multilingual Keyphrase Generation with Retriever-Generator Iterative Training
  7. 2025The Prompt is Mightier than the Example
  8. 2025Flaw or Artifact? Rethinking Prompt Sensitivity in Evaluating LLMs