mlsanityData to 14 Oct 2026

Clip-Tuning: Towards Derivative-free Prompt Learning with a Mixture of Rewards

arXiv 2210.12050 ↗First posted 21 Oct 2022cs.CLcited by 14

Not on the map. Why?

Abstract (arXiv)

Derivative-free prompt learning has emerged as a lightweight alternative to prompt tuning, which only requires model inference to optimize the prompts. However, existing work did not take full advantage of the over-parameterized characteristics of large pre-trained language models (PLMs). In this paper, we propose Clip-Tuning, a simple yet effective method that adopts diverse frozen "thinned" networks of PLMs to obtain a mixture of rewards and thus advance the derivative-free prompt learning. The thinned networks consist of all the hidden units that survive a stationary dropout strategy, whose inference predictions reflect an ensemble of partial views over prompted training samples. Our method outperforms previous gradient-free prompt learning methods and achieves parity with gradient-based counterparts on seven language understanding benchmarks under few-shot settings.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 32 of its 40 references that are in the map. First posted on arXiv 21 Oct 2022.

Builds on

32 of 40 references.

References · 32

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  4. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  5. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,899
  6. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
  7. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,915
  8. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
  9. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,682
  10. 2015Character-level Convolutional Networks for Text Classificationcited by 2,330
  11. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,262
  12. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,173
20 more
  1. 2015A large annotated corpus for learning natural language inferencecited by 1,847
  2. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,256
  3. 2021Scaling Language Models: Methods, Analysis & Insights from Training Gophercited by 1,202
  4. 2020Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inferencecited by 938
  5. 2018A Tutorial on Bayesian Optimizationcited by 744
  6. 2021GPT Understands, Toocited by 716
  7. 2020Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuningcited by 671
  8. 2020The Lottery Ticket Hypothesis for Pre-trained BERT Networkscited by 275
  9. 2022Black-Box Tuning for Language-Model-as-a-Servicecited by 256
  10. 2020Revisiting Few-sample BERT Fine-tuningcited by 238
  11. 2021PPT: Pre-trained Prompt Tuning for Few-shot Learningcited by 232
  12. 2021R-Drop: Regularized Dropout for Neural Networkscited by 202
  13. 2021How Many Data Points is a Prompt Worth?cited by 198
  14. 2020Training independent subnetworks for robust predictioncited by 177
  15. 2019To Tune or Not to Tune? Adapting Pretrained Representations to Diverse Taskscited by 167
  16. 2022GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Modelscited by 127
  17. 2020Few-Shot Text Generation with Pattern-Exploiting Trainingcited by 87
  18. 2022Black-box Prompt Learning for Pre-trained Language Modelscited by 70
  19. 2021ERNIE 3.0 Titan: Exploring Larger-scale Knowledge Enhanced Pre-training for Language Understanding and Generationcited by 46
  20. 2022Diverse Lottery Tickets Boost Ensemble from a Single Pretrained Modelcited by 7

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 7; 2024: 5; 2025: 1.

14 papers.

Sort:

By area:

  1. 2023Fine-Tuning Language Models with Just Forward Passescited by 345
  2. 2023Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Surveycited by 135
  3. 2024Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmarkcited by 114
  4. 2024Evolutionary Computation in the Era of Large Language Model: Survey and Roadmapcited by 90
  5. 2022PromptBoosting: Black-Box Text Classification with Ten Forward Passescited by 36
  6. 2023Language Models as Black-Box Optimizers for Vision-Language Modelscited by 36
  7. 2024Prompt Optimization with Human Feedbackcited by 35
  8. 2023Use Your INSTINCT: INSTruction optimization for LLMs usIng Neural bandits Coupled with Transformerscited by 30
  9. 2023Gradient-Free Textual Inversioncited by 29
  10. 2023Small Language Models Improve Giants by Rewriting Their Outputscited by 18
  11. 2025EvolKV: Evolutionary KV Cache Compression for LLM Inferencecited by 10
  12. 2023Make Prompt-based Black-Box Tuning Colorful: Boosting Model Generalization from Three Orthogonal Perspectivescited by 5
2 more
  1. 2024Putting People in LLMs' Shoes: Generating Better Answers via Question Rewritercited by 4
  2. 2024ACING: Actor-Critic for Instruction Learning in Black-Box LLMscited by 2