mlsanityData to 7 Oct 2026

Active Example Selection for In-Context Learning

arXiv 2211.04486 ↗First posted 8 Nov 2022cs.CL cs.AIcited by 195

Not on the map. Why?

Abstract (arXiv)

With a handful of demonstration examples, large-scale language models show strong capability to perform various tasks by in-context learning from these examples, without any fine-tuning. We demonstrate that in-context learning performance can be highly unstable across samples of examples, indicating the idiosyncrasies of how language models acquire information. We formulate example selection for in-context learning as a sequential decision problem, and propose a reinforcement learning algorithm for identifying generalizable policies to select demonstration examples. For GPT-2, our learned policies demonstrate strong abilities of generalizing to unseen tasks in training, with a 5.8% improvement on average. Examples selected from our learned policies can even achieve a small improvement on GPT-3 Ada. However, the improvement diminishes on larger GPT-3 models, suggesting emerging capabilities of large language models.

Key facts. Cited by 195 papers in the map (data through 7 Oct 2026). Builds on 30 of its 45 references that are in the map. First posted on arXiv 8 Nov 2022.

Builds on

30 of 45 references.

References · 30

  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. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  5. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  6. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  7. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  8. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  9. 2022Emergent Abilities of Large Language Modelscited by 2,483
  10. 2015Character-level Convolutional Networks for Text Classificationcited by 2,293
  11. 2020Conservative Q-Learning for Offline Reinforcement Learningcited by 1,777
  12. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
18 more
  1. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,413
  2. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,371
  3. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,255
  4. 2021Scaling Language Models: Methods, Analysis & Insights from Training Gophercited by 1,199
  5. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,184
  6. 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,173
  7. 2021Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivitycited by 1,122
  8. 2021An Explanation of In-context Learning as Implicit Bayesian Inferencecited by 915
  9. 2017Rainbow: Combining Improvements in Deep Reinforcement Learningcited by 774
  10. 2021Learning To Retrieve Prompts for In-Context Learningcited by 641
  11. 2021True Few-Shot Learning with Language Modelscited by 343
  12. 2021Surface Form Competition: Why the Highest Probability Answer Isn't Always Rightcited by 256
  13. 2021SPoT: Better Frozen Model Adaptation through Soft Prompt Transfercited by 235
  14. 2022A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problemscited by 228
  15. 2021Reframing Instructional Prompts to GPTk's Languagecited by 176
  16. 2017Learning how to Active Learn: A Deep Reinforcement Learning Approachcited by 79
  17. 2022IDPG: An Instance-Dependent Prompt Generation Methodcited by 43
  18. 2021The Dangers of Underclaiming: Reasons for Caution When Reporting How NLP Systems Failcited by 38

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 55; 2024: 71; 2025: 42; 2026: 25.

195 papers.

Sort:

By area:

  1. 2023A Survey of Large Language Modelscited by 2,537
  2. 2022A Survey on In-context Learningcited by 717
  3. 2023Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrationscited by 401
  4. 2023The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learningcited by 251
  5. 2023Prompting Large Language Model for Machine Translation: A Case Studycited by 247
  6. 2024CodeS: Towards Building Open-source Language Models for Text-to-SQLcited by 183
  7. 2023Unified Demonstration Retriever for In-Context Learningcited by 141
  8. 2023Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Datacited by 119
  9. 2023Finding Support Examples for In-Context Learningcited by 104
  10. 2023LayoutLLM-T2I: Eliciting Layout Guidance from LLM for Text-to-Image Generationcited by 92
  11. 2023Pearl: Personalizing Large Language Model Writing Assistants with Generation-Calibrated Retrieverscited by 91
  12. 2023In-Context Learning with Iterative Demonstration Selectioncited by 74
38 more
  1. 2024In-context Learning with Retrieved Demonstrations for Language Models: A Surveycited by 69
  2. 2023Learning to Retrieve In-Context Examples for Large Language Modelscited by 60
  3. 2023GPT4AIGChip: Towards Next-Generation AI Accelerator Design Automation via Large Language Modelscited by 59
  4. 2022Data Curation Alone Can Stabilize In-context Learningcited by 58
  5. 2023Active Learning Principles for In-Context Learning with Large Language Modelscited by 53
  6. 2023How Do In-Context Examples Affect Compositional Generalization?cited by 51
  7. 2023Privacy-Preserving In-Context Learning for Large Language Modelscited by 50
  8. 2023In-Context Learning Learns Label Relationships but Is Not Conventional Learningcited by 48
  9. 2024Universal Vulnerabilities in Large Language Models: Backdoor Attacks for In-context Learningcited by 47
  10. 2023Skill-Based Few-Shot Selection for In-Context Learningcited by 46
  11. 2023Enhancing Few-shot Text-to-SQL Capabilities of Large Language Models: A Study on Prompt Design Strategiescited by 44
  12. 2023Exploring Effective Factors for Improving Visual In-Context Learningcited by 43
  13. 2023Small Models are Valuable Plug-ins for Large Language Modelscited by 42
  14. 2023Self-ICL: Zero-Shot In-Context Learning with Self-Generated Demonstrationscited by 42
  15. 2024Can Language Models Perform Robust Reasoning in Chain-of-thought Prompting with Noisy Rationales?cited by 40
  16. 2025A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoningcited by 40
  17. 2023ChatGPT Evaluation on Sentence Level Relations: A Focus on Temporal, Causal, and Discourse Relationscited by 39
  18. 2024Prompt Optimization with EASE? Efficient Ordering-aware Automated Selection of Exemplarscited by 37
  19. 2023Which Examples to Annotate for In-Context Learning? Towards Effective and Efficient Selectioncited by 36
  20. 2023The Mystery of In-Context Learning: A Comprehensive Survey on Interpretation and Analysiscited by 34
  21. 2025Emergent Abilities in Large Language Models: A Surveycited by 34
  22. 2024PromptWizard: Task-Aware Prompt Optimization Frameworkcited by 32
  23. 2023Large Language Model Instruction Following: A Survey of Progresses and Challengescited by 31
  24. 2023Interactive Natural Language Processingcited by 31
  25. 2023How to Configure Good In-Context Sequence for Visual Question Answeringcited by 31
  26. 2024Smoothie: Label Free Language Model Routingcited by 31
  27. 2024LLMs Are In-Context Bandit Reinforcement Learnerscited by 27
  28. 2024Do Large Language Models Perform Latent Multi-Hop Reasoning without Exploiting Shortcuts?cited by 26
  29. 2024Retrieval Augmented Fact Verification by Synthesizing Contrastive Argumentscited by 25
  30. 2023RetICL: Sequential Retrieval of In-Context Examples with Reinforcement Learningcited by 24
  31. 2024A Trembling House of Cards? Mapping Adversarial Attacks against Language Agentscited by 22
  32. 2024Large Language Model Agent as a Mechanical Designercited by 20
  33. 2024BeHonest: Benchmarking Honesty in Large Language Modelscited by 20
  34. 2024Assistive Large Language Model Agents for Socially-Aware Negotiation Dialoguescited by 18
  35. 2024Superiority of Multi-Head Attention in In-Context Linear Regressioncited by 17
  36. 2024Comparing Specialised Small and General Large Language Models on Text Classification: 100 Labelled Samples to Achieve Break-Even Performancecited by 17
  37. 2024ActiveLLM: Large Language Model-based Active Learning for Textual Few-Shot Scenarioscited by 17
  38. 2024Task Facet Learning: A Structured Approach to Prompt Optimizationcited by 17

50 most cited of 195 All 195 (JSON)