mlsanityData to 14 Oct 2026

Universal Self-Adaptive Prompting

arXiv 2305.14926 ↗First posted 24 May 2023cs.CL cs.AI cs.LGcited by 14

Not on the map. Why?

Abstract (arXiv)

A hallmark of modern large language models (LLMs) is their impressive general zero-shot and few-shot abilities, often elicited through in-context learning (ICL) via prompting. However, while highly coveted and being the most general, zero-shot performances in LLMs are still typically weaker due to the lack of guidance and the difficulty of applying existing automatic prompt design methods in general tasks when ground-truth labels are unavailable. In this study, we address this by presenting Universal Self-Adaptive Prompting (USP), an automatic prompt design approach specifically tailored for zero-shot learning (while compatible with few-shot). Requiring only a small amount of unlabeled data and an inference-only LLM, USP is highly versatile: to achieve universal prompting, USP categorizes a possible NLP task into one of the three possible task types and then uses a corresponding selector to select the most suitable queries and zero-shot model-generated responses as pseudo-demonstrations, thereby generalizing ICL to the zero-shot setup in a fully automated way. We evaluate USP with PaLM and PaLM 2 models and demonstrate performances that are considerably stronger than standard zero-shot baselines and often comparable to or even superior to few-shot baselines across more than 40 natural language understanding, natural language generation, and reasoning tasks.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 57 of its 94 references that are in the map. First posted on arXiv 24 May 2023.

Builds on

57 of 94 references.

References · 57

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  5. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  6. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  7. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  8. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,899
  9. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,886
  10. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  11. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,915
  12. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
38 more
  1. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  2. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  3. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  4. 2022Emergent Abilities of Large Language Modelscited by 2,512
  5. 2019BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questionscited by 2,183
  6. 2022Language Models (Mostly) Know What They Knowcited by 1,856
  7. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,807
  8. 2019SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systemscited by 1,729
  9. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,554
  10. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,470
  11. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,434
  12. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,392
  13. 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,317
  14. 2020BLEURT: Learning Robust Metrics for Text Generationcited by 1,203
  15. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,195
  16. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,045
  17. 2016The LAMBADA dataset: Word prediction requiring a broad discourse contextcited by 992
  18. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 920
  19. 2017RACE: Large-scale ReAding Comprehension Dataset From Examinationscited by 861
  20. 2019Adversarial NLI: A New Benchmark for Natural Language Understandingcited by 807
  21. 2022Automatic Chain of Thought Prompting in Large Language Modelscited by 688
  22. 2022Large Language Models Can Self-Improvecited by 664
  23. 2021Learning To Retrieve Prompts for In-Context Learningcited by 648
  24. 2021Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigmcited by 606
  25. 2021Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Modelscited by 463
  26. 2016Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learningcited by 441
  27. 2022Unnatural Instructions: Tuning Language Models with (Almost) No Human Laborcited by 397
  28. 2023Larger language models do in-context learning differentlycited by 394
  29. 2018WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representationscited by 372
  30. 2022RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learningcited by 366
  31. 2023Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discoverycited by 336
  32. 2022UL2: Unifying Language Learning Paradigmscited by 295
  33. 2017Zero-Shot Learning -- The Good, the Bad and the Uglycited by 255
  34. 2021Generating Datasets with Pretrained Language Modelscited by 193
  35. 2021Reframing Instructional Prompts to GPTk's Languagecited by 176
  36. 2020WikiLingua: A New Benchmark Dataset for Cross-Lingual Abstractive Summarizationcited by 154
  37. 2021Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Modelscited by 139
  38. 2022GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Modelscited by 127

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 5; 2025: 4; 2026: 2.

14 papers.

Sort:

By area:

  1. 2023In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steeringcited by 245
  2. 2024Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluatorscited by 149
  3. 2023Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineeringcited by 94
  4. 2025From Few to Many: Self-Improving Many-Shot Reasoners Through Iterative Optimization and Generationcited by 21
  5. 2024The Impact of Demonstrations on Multilingual In-Context Learning: A Multidimensional Analysiscited by 13
  6. 2023Towards Informative Few-Shot Prompt with Maximum Information Gain for In-Context Learningcited by 9
  7. 2025Bottom-Up Synthesis of Knowledge-Grounded Task-Oriented Dialogues with Iteratively Self-Refined Promptscited by 5
  8. 2024Let's Be Self-generated via Step by Step: A Curriculum Learning Approach to Automated Reasoning with Large Language Modelscited by 4
  9. 2026PromptAudit: Auditing Prompt Sensitivity in LLM-Based Vulnerability Detectioncited by 2
  10. 2024In-context Demonstration Matters: On Prompt Optimization for Pseudo-Supervision Refinementcited by 1
  11. 2024What Is Wrong with My Model? Identifying Systematic Problems with Semantic Data Slicingcited by 0
  12. 2025Efficient Knowledge Feeding to Language Models: A Novel Integrated Encoder-Decoder Architecturecited by 0
2 more
  1. 2025BRAID: Bounded Reasoning for Autonomous Inference and Decisionscited by 0
  2. 2026Self-Improving In-Context Learningcited by 0