mlsanityData to 7 Oct 2026

GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Models

arXiv 2203.07281 ↗First posted 14 Mar 2022cs.CL cs.AI cs.LGcited by 127

Not on the map. Why?

Abstract (arXiv)

Providing natural language instructions in prompts is a useful new paradigm for improving task performance of large language models in a zero-shot setting. Recent work has aimed to improve such prompts via manual rewriting or gradient-based tuning. However, manual rewriting is time-consuming and requires subjective interpretation, while gradient-based tuning can be extremely computationally demanding for large models and may not be feasible for API-based models. In this work, we introduce Gradient-free Instructional Prompt Search (GrIPS), a gradient-free, edit-based search approach for improving task instructions for large language models. GrIPS takes in instructions designed for humans and automatically returns an improved, edited prompt, while allowing for API-based tuning. With InstructGPT models, GrIPS improves the average task performance by up to 4.30 percentage points on eight classification tasks from the Natural Instructions dataset (with similar improvements for OPT, BLOOM, and FLAN-T5). We see improvements for both instruction-only prompts and instruction + k-shot examples prompts. Notably, GrIPS outperforms manual rewriting and purely example-based prompts while controlling for the available compute and data budget. Further, performance of GrIPS is comparable to select gradient-based tuning approaches. Qualitatively, we show our edits can simplify instructions and at times make them incoherent but nonetheless improve accuracy. Our code is available at: https://github.com/archiki/GrIPS

Key facts. Cited by 127 papers in the map (data through 7 Oct 2026). Builds on 40 of its 63 references that are in the map. First posted on arXiv 14 Mar 2022.

Builds on

40 of 63 references.

References · 40

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  4. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  5. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  6. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  7. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,222
  8. 2019Language Models as Knowledge Bases?cited by 1,922
  9. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,462
  10. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,413
  11. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,371
  12. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,255
28 more
  1. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,184
  2. 2021Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivitycited by 1,122
  3. 2019PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarizationcited by 1,100
  4. 2021Ethical and social risks of harm from Language Modelscited by 957
  5. 2019How Can We Know What Language Models Know?cited by 953
  6. 2020Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inferencecited by 934
  7. 2021An Explanation of In-context Learning as Implicit Bayesian Inferencecited by 915
  8. 2021GPT Understands, Toocited by 715
  9. 2019Universal Adversarial Triggers for Attacking and Analyzing NLPcited by 709
  10. 2021Cross-Task Generalization via Natural Language Crowdsourcing Instructionscited by 696
  11. 2020It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learnerscited by 668
  12. 2021Learning How to Ask: Querying LMs with Mixtures of Soft Promptscited by 376
  13. 2021True Few-Shot Learning with Language Modelscited by 343
  14. 2021Do Prompt-Based Models Really Understand the Meaning of their Prompts?cited by 324
  15. 2022Black-Box Tuning for Language-Model-as-a-Servicecited by 254
  16. 2021How Many Data Points is a Prompt Worth?cited by 197
  17. 2021Reframing Instructional Prompts to GPTk's Languagecited by 176
  18. 2022Impact of Pretraining Term Frequencies on Few-Shot Reasoningcited by 142
  19. 2021Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Modelscited by 139
  20. 2021Improving and Simplifying Pattern Exploiting Trainingcited by 97
  21. 2020Few-Shot Text Generation with Pattern-Exploiting Trainingcited by 87
  22. 2020The Turking Test: Can Language Models Understand Instructions?cited by 82
  23. 2020Learning from Task Descriptionscited by 78
  24. 2017Learning with Latent Languagecited by 75
  25. 2021Prompt Waywardness: The Curious Case of Discretized Interpretation of Continuous Promptscited by 64
  26. 2021Reordering Examples Helps during Priming-based Few-Shot Learningcited by 50
  27. 2020Iterative Edit-Based Unsupervised Sentence Simplificationcited by 33
  28. 2020Fast Interleaved Bidirectional Sequence Generationcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 15; 2023: 37; 2024: 37; 2025: 21; 2026: 17.

127 papers.

Sort:

By area:

  1. 2023Large Language Models as Optimizerscited by 830
  2. 2023Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formattingcited by 778
  3. 2022Ignore Previous Prompt: Attack Techniques For Language Modelscited by 760
  4. 2023Automatic Prompt Optimization with "Gradient Descent" and Beam Searchcited by 628
  5. 2022RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learningcited by 361
  6. 2023Fine-Tuning Language Models with Just Forward Passescited by 337
  7. 2023Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discoverycited by 329
  8. 2023PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimizationcited by 226
  9. 2023EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizerscited by 189
  10. 2022Self-Adaptive In-Context Learning: An Information Compression Perspective for In-Context Example Selection and Orderingcited by 158
  11. 2022Instruction Induction: From Few Examples to Natural Language Task Descriptionscited by 152
  12. 2023Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Surveycited by 134
38 more
  1. 2024Personalized Language Modeling from Personalized Human Feedbackcited by 124
  2. 2024Black-Box Access is Insufficient for Rigorous AI Auditscited by 123
  3. 2022Evaluating and Inducing Personality in Pre-trained Language Modelscited by 122
  4. 2023Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Datacited by 119
  5. 2024Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmarkcited by 113
  6. 2023Explore, Establish, Exploit: Red Teaming Language Models from Scratchcited by 111
  7. 2025A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deploymentcited by 110
  8. 2024Symbolic Learning Enables Self-Evolving Agentscited by 104
  9. 2023Guiding Large Language Models via Directional Stimulus Promptingcited by 94
  10. 2023Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning with Multimodal Modelscited by 91
  11. 2023Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineeringcited by 91
  12. 2024Evolutionary Computation in the Era of Large Language Model: Survey and Roadmapcited by 89
  13. 2024Efficient multi-prompt evaluation of LLMscited by 72
  14. 2024Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wiselycited by 65
  15. 2023DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineercited by 56
  16. 2022BBTv2: Towards a Gradient-Free Future with Large Language Modelscited by 53
  17. 2022TEMPERA: Test-Time Prompting via Reinforcement Learningcited by 50
  18. 2022Toward Human Readable Prompt Tuning: Kubrick's The Shining is a good movie, and a good prompt too?cited by 49
  19. 2023A Practical Survey on Zero-shot Prompt Design for In-context Learningcited by 49
  20. 2024Efficient Prompting Methods for Large Language Models: A Surveycited by 46
  21. 2023Discrete Prompt Compression with Reinforcement Learningcited by 42
  22. 2024When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Modelscited by 41
  23. 2023Did You Read the Instructions? Rethinking the Effectiveness of Task Definitions in Instruction Learningcited by 40
  24. 2022GPS: Genetic Prompt Search for Efficient Few-shot Learningcited by 37
  25. 2024Are Large Language Models Good Prompt Optimizers?cited by 37
  26. 2024Prompt Optimization with EASE? Efficient Ordering-aware Automated Selection of Exemplarscited by 37
  27. 2022PromptBoosting: Black-Box Text Classification with Ten Forward Passescited by 36
  28. 2023Language Models as Black-Box Optimizers for Vision-Language Modelscited by 36
  29. 2024On the Worst Prompt Performance of Large Language Modelscited by 36
  30. 2024Efficient Prompt Optimization Through the Lens of Best Arm Identificationcited by 35
  31. 2024Prompt Optimization with Human Feedbackcited by 35
  32. 2024Unleashing the Potential of Large Language Models as Prompt Optimizers: Analogical Analysis with Gradient-based Model Optimizerscited by 33
  33. 2023Joint Prompt Optimization of Stacked LLMs using Variational Inferencecited by 32
  34. 2023Preference-grounded Token-level Guidance for Language Model Fine-tuningcited by 31
  35. 2024Few-shot Personalization of LLMs with Mis-aligned Responsescited by 30
  36. 2023Use Your INSTINCT: INSTruction optimization for LLMs usIng Neural bandits Coupled with Transformerscited by 29
  37. 2022Causally Testing Gender Bias in LLMs: A Case Study on Occupational Biascited by 28
  38. 2024APEER: Automatic Prompt Engineering Enhances Large Language Model Rerankingcited by 28

50 most cited of 127 All 127 (JSON)