mlsanityData to 7 Oct 2026

Toward Human Readable Prompt Tuning: Kubrick's The Shining is a good movie, and a good prompt too?

arXiv 2212.10539 ↗First posted 20 Dec 2022cs.CLcited by 49

Not on the map. Why?

Abstract (arXiv)

Large language models can perform new tasks in a zero-shot fashion, given natural language prompts that specify the desired behavior. Such prompts are typically hand engineered, but can also be learned with gradient-based methods from labeled data. However, it is underexplored what factors make the prompts effective, especially when the prompts are natural language. In this paper, we investigate common attributes shared by effective prompts. We first propose a human readable prompt tuning method (F LUENT P ROMPT) based on Langevin dynamics that incorporates a fluency constraint to find a diverse distribution of effective and fluent prompts. Our analysis reveals that effective prompts are topically related to the task domain and calibrate the prior probability of label words. Based on these findings, we also propose a method for generating prompts using only unlabeled data, outperforming strong baselines by an average of 7.0% accuracy across three tasks.

Key facts. Cited by 49 papers in the map (data through 7 Oct 2026). Builds on 30 of its 38 references that are in the map. First posted on arXiv 20 Dec 2022.

Builds on

30 of 38 references.

References · 30

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  3. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  4. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  5. 2020The Pile: An 800GB Dataset of Diverse Text for Language Modelingcited by 2,346
  6. 2015Character-level Convolutional Networks for Text Classificationcited by 2,293
  7. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,462
  8. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,413
  9. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,371
  10. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,184
  11. 2021Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivitycited by 1,122
  12. 2015A Diversity-Promoting Objective Function for Neural Conversation Modelscited by 1,068
18 more
  1. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,020
  2. 2020Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inferencecited by 934
  3. 2022Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Taskscited by 858
  4. 2021GPT Understands, Toocited by 715
  5. 2021Cross-Task Generalization via Natural Language Crowdsourcing Instructionscited by 696
  6. 2021Learning How to Ask: Querying LMs with Mixtures of Soft Promptscited by 376
  7. 2022RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learningcited by 361
  8. 2022One Embedder, Any Task: Instruction-Finetuned Text Embeddingscited by 329
  9. 2021Do Prompt-Based Models Really Understand the Meaning of their Prompts?cited by 324
  10. 2022PromptSource: An Integrated Development Environment and Repository for Natural Language Promptscited by 288
  11. 2021Surface Form Competition: Why the Highest Probability Answer Isn't Always Rightcited by 256
  12. 2021WARP: Word-level Adversarial ReProgrammingcited by 220
  13. 2022Demystifying Prompts in Language Models via Perplexity Estimationcited by 215
  14. 2021OpenPrompt: An Open-source Framework for Prompt-learningcited by 148
  15. 2022GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Modelscited by 127
  16. 2022On the Relation between Sensitivity and Accuracy in In-context Learningcited by 71
  17. 2021Prompt Waywardness: The Curious Case of Discretized Interpretation of Continuous Promptscited by 64
  18. 2022Gradient-Based Constrained Sampling from Language Modelscited by 64

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 17; 2024: 17; 2025: 10; 2026: 5.

49 papers.

Sort:

By area:

  1. 2023Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formattingcited by 778
  2. 2023Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discoverycited by 329
  3. 2023Ring-A-Bell! How Reliable are Concept Removal Methods for Diffusion Models?cited by 239
  4. 2023EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizerscited by 189
  5. 2023Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Promptscited by 161
  6. 2023Explore, Establish, Exploit: Red Teaming Language Models from Scratchcited by 111
  7. 2023Explaining black box text modules in natural language with language modelscited by 61
  8. 2023DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineercited by 56
  9. 2023Active Learning Principles for In-Context Learning with Large Language Modelscited by 53
  10. 2023A Practical Survey on Zero-shot Prompt Design for In-context Learningcited by 49
  11. 2023What's the Magic Word? A Control Theory of LLM Promptingcited by 41
  12. 2023Language Models as Black-Box Optimizers for Vision-Language Modelscited by 36
37 more
  1. 2024On the Worst Prompt Performance of Large Language Modelscited by 36
  2. 2024Efficient Prompt Optimization Through the Lens of Best Arm Identificationcited by 35
  3. 2024Prompt Optimization with Human Feedbackcited by 35
  4. 2023Use Your INSTINCT: INSTruction optimization for LLMs usIng Neural bandits Coupled with Transformerscited by 29
  5. 2025PR-Attack: Coordinated Prompt-RAG Attacks on Retrieval-Augmented Generation in Large Language Models via Bilevel Optimizationcited by 29
  6. 2024SPRIG: Improving Large Language Model Performance by System Prompt Optimizationcited by 28
  7. 2023Auto-Instruct: Automatic Instruction Generation and Ranking for Black-Box Language Modelscited by 21
  8. 2025PromptSculptor: Multi-Agent Based Text-to-Image Prompt Optimizationcited by 19
  9. 2024GReaTer: Gradients over Reasoning Makes Smaller Language Models Strong Prompt Optimizerscited by 12
  10. 2023Selective Perception: Optimizing State Descriptions with Reinforcement Learning for Language Model Actorscited by 9
  11. 2024FLRT: Fluent Student-Teacher Redteamingcited by 9
  12. 2023Prompts have evil twinscited by 7
  13. 2023Strings from the Library of Babel: Random Sampling as a Strong Baseline for Prompt Optimisationcited by 7
  14. 2025Meta-Prompt Optimization for LLM-Based Sequential Decision Makingcited by 7
  15. 2024Hard Prompts Made Interpretable: Sparse Entropy Regularization for Prompt Tuning with RLcited by 6
  16. 2025CAPO: Cost-Aware Prompt Optimizationcited by 6
  17. 2024Fluent dreaming for language modelscited by 5
  18. 2024Defining and Detecting Vulnerability in Human Evaluation Guidelines: A Preliminary Study Towards Reliable NLG Evaluationcited by 5
  19. 2025Same Question, Different Words: A Latent Adversarial Framework for Prompt Robustnesscited by 5
  20. 2026nabla-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Latent Spacecited by 4
  21. 2024Putting People in LLMs' Shoes: Generating Better Answers via Question Rewritercited by 3
  22. 2025A Toolbox for Improving Evolutionary Prompt Searchcited by 3
  23. 2024RIFF: Learning to Rephrase Inputs for Few-shot Fine-tuning of Language Modelscited by 2
  24. 2024LoPT: Low-Rank Prompt Tuning for Parameter Efficient Language Modelscited by 2
  25. 2024ACING: Actor-Critic for Instruction Learning in Black-Box LLMscited by 2
  26. 2024Learning Personalized Prompts for Healthcare Guidancecited by 2
  27. 2025Rethinking the Vulnerability of Concept Erasure and a New Methodcited by 2
  28. 2025RiOT: Efficient Prompt Refinement with Residual Optimization Treecited by 2
  29. 2025GPT, But Backwards: Exactly Inverting Language Model Outputscited by 2
  30. 2026LPDS: Evaluating LLM Robustness Through Logic-Preserving Difficulty Scalingcited by 2
  31. 2024On the Transformations across Reward Model, Parameter Update, and In-Context Promptcited by 1
  32. 2024FUSE-ing Language Models: Zero-Shot Adapter Discovery for Prompt Optimization Across Tokenizerscited by 1
  33. 2024Label Set Optimization via Activation Distribution Kurtosis for Zero-shot Classification with Generative Modelscited by 0
  34. 2025Seeing Through the Brain: New Insights from Decoding Visual Stimuli with fMRIcited by 0
  35. 2026GFlowPO: Generative Flow Network as a Language Model Prompt Optimizercited by 0
  36. 2026To Write or to Automate Linguistic Prompts, That Is the Questioncited by 0
  37. 2026Learning to Translate from Soft to Hard LLM Promptscited by 0