mlsanityData to 7 Oct 2026

RIFF: Learning to Rephrase Inputs for Few-shot Fine-tuning of Language Models

arXiv 2403.02271 ↗First posted 4 Mar 2024cs.CL cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Pre-trained Language Models (PLMs) can be accurately fine-tuned for downstream text processing tasks. Recently, researchers have introduced several parameter-efficient fine-tuning methods that optimize input prompts or adjust a small number of model parameters (e.g LoRA). In this study, we explore the impact of altering the input text of the original task in conjunction with parameter-efficient fine-tuning methods. To most effectively rewrite the input text, we train a few-shot paraphrase model with a Maximum-Marginal Likelihood objective. Using six few-shot text classification datasets, we show that enriching data with paraphrases at train and test time enhances the performance beyond what can be achieved with parameter-efficient fine-tuning alone. The code used for our experiments can be found at https://github.com/SaeedNajafi/RIFF.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 46 of its 67 references that are in the map. First posted on arXiv 4 Mar 2024.

Builds on

46 of 67 references.

References · 46

  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. 2022Training language models to follow instructions with human feedbackcited by 15,712
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  5. 2017Proximal Policy Optimization Algorithmscited by 14,441
  6. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  7. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  8. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  9. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  10. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  11. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  12. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
34 more
  1. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  2. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  3. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  4. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  5. 2015Character-level Convolutional Networks for Text Classificationcited by 2,293
  6. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,222
  7. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,218
  8. 2019Language Models as Knowledge Bases?cited by 1,922
  9. 2017Decoupled Weight Decay Regularizationcited by 1,722
  10. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,255
  11. 2018Averaging Weights Leads to Wider Optima and Better Generalizationcited by 1,194
  12. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,020
  13. 2019On the Convergence of Adam and Beyondcited by 834
  14. 2019EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Taskscited by 800
  15. 2016Self-critical Sequence Training for Image Captioningcited by 544
  16. 2021A Survey of Data Augmentation Approaches for NLPcited by 408
  17. 2022RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learningcited by 361
  18. 2021Towards Understanding and Mitigating Social Biases in Language Modelscited by 294
  19. 2022Black-Box Tuning for Language-Model-as-a-Servicecited by 254
  20. 2022Making Large Language Models Better Reasoners with Step-Aware Verifiercited by 231
  21. 2022DyLoRA: Parameter Efficient Tuning of Pre-trained Models using Dynamic Search-Free Low-Rank Adaptationcited by 229
  22. 2020Exploring Versatile Generative Language Model Via Parameter-Efficient Transfer Learningcited by 139
  23. 2021An Empirical Survey of Data Augmentation for Limited Data Learning in NLPcited by 101
  24. 2017Paraphrase Generation with Deep Reinforcement Learningcited by 58
  25. 2018Memory Augmented Policy Optimization for Program Synthesis and Semantic Parsingcited by 57
  26. 2022Toward Human Readable Prompt Tuning: Kubrick's The Shining is a good movie, and a good prompt too?cited by 49
  27. 2017From Language to Programs: Bridging Reinforcement Learning and Maximum Marginal Likelihoodcited by 41
  28. 2021Efficient (Soft) Q-Learning for Text Generation with Limited Good Datacited by 35
  29. 2020Unsupervised Paraphrasing via Deep Reinforcement Learningcited by 25
  30. 2023LM-CPPF: Paraphrasing-Guided Data Augmentation for Contrastive Prompt-Based Few-Shot Fine-Tuningcited by 15
  31. 2019An Empirical Comparison on Imitation Learning and Reinforcement Learning for Paraphrase Generationcited by 11
  32. 2021Unsupervised Contextual Paraphrase Generation using Lexical Control and Reinforcement Learningcited by 10
  33. 2022Decoder Tuning: Efficient Language Understanding as Decodingcited by 6
  34. 2023Weakly-Supervised Questions for Zero-Shot Relation Extractioncited by 2

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025From Generation to Generalization: Emergent Few-Shot Learning in Video Diffusion Modelscited by 7
  2. 2025Offline Preference Optimization via Maximum Marginal Likelihood Estimationcited by 1