mlsanityData to 14 Oct 2026

In-Context Learning Demonstration Selection via Influence Analysis

arXiv 2402.11750 ↗First posted 19 Feb 2024cs.CLcited by 11

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) have showcased their In-Context Learning (ICL) capabilities, enabling few-shot learning without the need for gradient updates. Despite its advantages, the effectiveness of ICL heavily depends on the choice of demonstrations. Selecting the most effective demonstrations for ICL remains a significant research challenge. To tackle this issue, we propose a demonstration selection method named InfICL, which utilizes influence functions to analyze impacts of training samples. By identifying the most influential training samples as demonstrations, InfICL aims to enhance the ICL generalization performance. To keep InfICL cost-effective, we only use the LLM to generate sample input embeddings, avoiding expensive fine-tuning. Through empirical studies on various real-world datasets, we demonstrate advantages of InfICL compared to state-of-the-art baselines.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 32 of its 41 references that are in the map. First posted on arXiv 19 Feb 2024.

Builds on

32 of 41 references.

References · 32

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  4. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  5. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,234
  6. 2017Understanding Black-box Predictions via Influence Functionscited by 1,741
  7. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,256
  8. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,195
  9. 2018Neural Network Acceptability Judgmentscited by 958
  10. 2021An Explanation of In-context Learning as Implicit Bayesian Inferencecited by 938
  11. 2021Learning To Retrieve Prompts for In-Context Learningcited by 648
  12. 2020What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimationcited by 497
20 more
  1. 2023Studying Large Language Model Generalization with Influence Functionscited by 326
  2. 2021An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQAcited by 301
  3. 2020Influence Functions in Deep Learning Are Fragilecited by 252
  4. 2022Active Example Selection for In-Context Learningcited by 196
  5. 2022Self-Adaptive In-Context Learning: An Information Compression Perspective for In-Context Example Selection and Orderingcited by 161
  6. 2020Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functionscited by 144
  7. 2023Unified Demonstration Retriever for In-Context Learningcited by 142
  8. 2023Finding Support Examples for In-Context Learningcited by 104
  9. 2018Understanding the Origins of Bias in Word Embeddingscited by 91
  10. 2023In-Context Learning with Iterative Demonstration Selectioncited by 74
  11. 2022On the Relation between Sensitivity and Accuracy in In-context Learningcited by 72
  12. 2023Dr.ICL: Demonstration-Retrieved In-context Learningcited by 72
  13. 2020Subpopulation Data Poisoning Attackscited by 70
  14. 2020Influence Function based Data Poisoning Attacks to Top-N Recommender Systemscited by 63
  15. 2023In-context Example Selection with Influencescited by 61
  16. 2022Data Curation Alone Can Stabilize In-context Learningcited by 59
  17. 2023How Many Demonstrations Do You Need for In-context Learning?cited by 52
  18. 2021Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updatescited by 27
  19. 2023RetICL: Sequential Retrieval of In-Context Examples with Reinforcement Learningcited by 24
  20. 2021Influence-guided Data Augmentation for Neural Tensor Completioncited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 7; 2026: 2.

11 papers.

  1. 2025TACO: Enhancing Multimodal In-context Learning via Task Mapping-Guided Sequence Configurationcited by 23
  2. 2024What Makes In-context Learning Effective for Mathematical Reasoning: A Theoretical Analysiscited by 7
  3. 2025DICE: Dynamic In-Context Example Selection in LLM Agents via Efficient Knowledge Transfercited by 5
  4. 2024Comparative Analysis of Demonstration Selection Algorithms for LLM In-Context Learningcited by 3
  5. 2025Unraveling Indirect In-Context Learning Using Influence Functionscited by 3
  6. 2025StaICC: Standardized Evaluation for Classification Task in In-context Learningcited by 2
  7. 2025Foundation of Intelligence: Review of Math Word Problems from Human Cognition Perspectivecited by 1
  8. 2025Mockingbird: How does LLM perform in general machine learning tasks?cited by 0
  9. 2025KITE: Kernelized and Information Theoretic Exemplars for In-Context Learningcited by 0
  10. 2026UCS: Estimating Unseen Coverage for Improved In-Context Learningcited by 0
  11. 2026Toward Robust In-Context Learning: Leveraging Out-of-distribution Proxies for Target Inaccessible Demonstration Retrievalcited by 0