mlsanityData to 14 Oct 2026

Learning to Select In-Context Demonstration Preferred by Large Language Model

arXiv 2505.19966 ↗First posted 26 May 2025cs.LG cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

In-context learning (ICL) enables large language models (LLMs) to adapt to new tasks during inference using only a few demonstrations. However, ICL performance is highly dependent on the selection of these demonstrations. Recent work explores retrieval-based methods for selecting query-specific demonstrations, but these approaches often rely on surrogate objectives such as metric learning, failing to directly optimize ICL performance. Consequently, they struggle to identify truly beneficial demonstrations. Moreover, their discriminative retrieval paradigm is ineffective when the candidate pool lacks sufficient high-quality demonstrations. To address these challenges, we propose GenICL, a novel generative preference learning framework that leverages LLM feedback to directly optimize demonstration selection for ICL. Experiments on 19 datasets across 11 task categories demonstrate that GenICL achieves superior performance than existing methods in selecting the most effective demonstrations, leading to better ICL performance.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 41 of its 56 references that are in the map. First posted on arXiv 26 May 2025.

Builds on

41 of 56 references.

References · 41

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2017Proximal Policy Optimization Algorithmscited by 15,215
  4. 2024The Llama 3 Herd of Modelscited by 14,715
  5. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  6. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  7. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  8. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  9. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  10. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,899
  11. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
  12. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,100
29 more
  1. 2017Deep reinforcement learning from human preferencescited by 3,912
  2. 2015Character-level Convolutional Networks for Text Classificationcited by 2,330
  3. 2019BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questionscited by 2,183
  4. 2018Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answeringcited by 2,164
  5. 2019Fine-Tuning Language Models from Human Preferencescited by 2,150
  6. 2015A large annotated corpus for learning natural language inferencecited by 1,847
  7. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,434
  8. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,253
  9. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,195
  10. 2021Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivitycited by 1,135
  11. 2021An Explanation of In-context Learning as Implicit Bayesian Inferencecited by 938
  12. 2021Learning To Retrieve Prompts for In-Context Learningcited by 648
  13. 2021MetaICL: Learning to Learn In Contextcited by 454
  14. 2019PAWS: Paraphrase Adversaries from Word Scramblingcited by 402
  15. 2024Teaching Large Language Models to Reason with Reinforcement Learningcited by 160
  16. 2023Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learningcited by 149
  17. 2020DART: Open-Domain Structured Data Record to Text Generationcited by 145
  18. 2023Compositional Exemplars for In-context Learningcited by 144
  19. 2023Unified Demonstration Retriever for In-Context Learningcited by 142
  20. 2023UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluationcited by 75
  21. 2022On the Relation between Sensitivity and Accuracy in In-context Learningcited by 72
  22. 2023Dr.ICL: Demonstration-Retrieved In-context Learningcited by 72
  23. 2024In-context Learning with Retrieved Demonstrations for Language Models: A Surveycited by 70
  24. 2019Semantic Noise Matters for Neural Natural Language Generationcited by 64
  25. 2019This Email Could Save Your Life: Introducing the Task of Email Subject Line Generationcited by 58
  26. 2024DemoRank: Selecting Effective Demonstrations for Large Language Models in Ranking Taskcited by 17
  27. 2024Learning to Retrieve Iteratively for In-Context Learningcited by 13
  28. 2024Effective Demonstration Annotation for In-Context Learning via Language Model-Based Determinantal Point Processcited by 9
  29. 2024Boosting Deductive Reasoning with Step Signals In RLHFcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026Learning to Select Visual In-Context Demonstrationscited by 2
  2. 2026Easier to Judge than to Find: Predicting In-Context Learning Success for Demonstration Selectioncited by 1
  3. 2026When Does Context Help? Error Dynamics of Contextual Information in Large Language Modelscited by 0
  4. 2026SCOPE: A Lightweight-training LLM Framework for Air Traffic Control Readback Monitoringcited by 0
  5. 2026Downstream-Aware Context Selection for Online In-Context Reinforcement Learningcited by 0