mlsanityData to 7 Oct 2026

PromptRefine: Enhancing Few-Shot Performance on Low-Resource Indic Languages with Example Selection from Related Example Banks

arXiv 2412.05710 ↗First posted 7 Dec 2024cs.CL cs.AI cs.IRcited by 5

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) have recently demonstrated impressive few-shot learning capabilities through in-context learning (ICL). However, ICL performance is highly dependent on the choice of few-shot demonstrations, making the selection of the most optimal examples a persistent research challenge. This issue is further amplified in low-resource Indic languages, where the scarcity of ground-truth data complicates the selection process. In this work, we propose PromptRefine, a novel Alternating Minimization approach for example selection that improves ICL performance on low-resource Indic languages. PromptRefine leverages auxiliary example banks from related high-resource Indic languages and employs multi-task learning techniques to align language-specific retrievers, enabling effective cross-language retrieval. Additionally, we incorporate diversity in the selected examples to enhance generalization and reduce bias. Through comprehensive evaluations on four text generation tasks -- Cross-Lingual Question Answering, Multilingual Question Answering, Machine Translation, and Cross-Lingual Summarization using state-of-the-art LLMs such as LLAMA-3.1-8B, LLAMA-2-7B, Qwen-2-7B, and Qwen-2.5-7B, we demonstrate that PromptRefine significantly outperforms existing frameworks for retrieving examples.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 49 of its 69 references that are in the map. First posted on arXiv 7 Dec 2024.

Builds on

49 of 69 references.

References · 49

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2024The Llama 3 Herd of Modelscited by 14,192
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  5. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  6. 2024Qwen2 Technical Reportcited by 2,076
  7. 2019SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systemscited by 1,718
  8. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,413
  9. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,371
  10. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,184
  11. 2018Hierarchical Neural Story Generationcited by 1,182
  12. 2021Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivitycited by 1,122
37 more
  1. 2021An Explanation of In-context Learning as Implicit Bayesian Inferencecited by 915
  2. 2021Learning To Retrieve Prompts for In-Context Learningcited by 641
  3. 2020Towards a Human-like Open-Domain Chatbotcited by 467
  4. 2021MetaICL: Learning to Learn In Contextcited by 450
  5. 2023Larger language models do in-context learning differentlycited by 386
  6. 2017Beam Search Strategies for Neural Machine Translationcited by 232
  7. 2022Why Can GPT Learn In-Context? Language Models Implicitly Perform Gradient Descent as Meta-Optimizerscited by 204
  8. 2022Active Example Selection for In-Context Learningcited by 195
  9. 2023Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Promptingcited by 163
  10. 2022Self-Adaptive In-Context Learning: An Information Compression Perspective for In-Context Example Selection and Orderingcited by 158
  11. 2023Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learningcited by 149
  12. 2023What In-Context Learning "Learns" In-Context: Disentangling Task Recognition and Task Learningcited by 149
  13. 2023IndicTrans2: Towards High-Quality and Accessible Machine Translation Models for all 22 Scheduled Indian Languagescited by 149
  14. 2023Compositional Exemplars for In-context Learningcited by 143
  15. 2023Unified Demonstration Retriever for In-Context Learningcited by 141
  16. 2022Diverse Demonstrations Improve In-context Compositional Generalizationcited by 136
  17. 2022Ground-Truth Labels Matter: A Deeper Look into Input-Label Demonstrationscited by 116
  18. 2021Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learnerscited by 115
  19. 2023Finding Support Examples for In-Context Learningcited by 104
  20. 2021Language Models are Few-shot Multilingual Learnerscited by 92
  21. 2023Do Multilingual Language Models Think Better in English?cited by 87
  22. 2022On the Effect of Pretraining Corpora on In-context Learning by a Large-scale Language Modelcited by 78
  23. 2023In-Context Learning with Iterative Demonstration Selectioncited by 74
  24. 2023Symbol tuning improves in-context learning in language modelscited by 72
  25. 2020A Mathematical Exploration of Why Language Models Help Solve Downstream Taskscited by 71
  26. 2023Multilingual LLMs are Better Cross-lingual In-context Learners with Alignmentcited by 71
  27. 2023Dr.ICL: Demonstration-Retrieved In-context Learningcited by 71
  28. 2022Building Machine Translation Systems for the Next Thousand Languagescited by 69
  29. 2024LLMs Are Few-Shot In-Context Low-Resource Language Learnerscited by 68
  30. 2023In-context Example Selection with Influencescited by 60
  31. 2023MEGAVERSE: Benchmarking Large Language Models Across Languages, Modalities, Models and Taskscited by 57
  32. 2022Improving In-Context Few-Shot Learning via Self-Supervised Trainingcited by 56
  33. 2024IndicGenBench: A Multilingual Benchmark to Evaluate Generation Capabilities of LLMs on Indic Languagescited by 55
  34. 2024Let's Learn Step by Step: Enhancing In-Context Learning Ability with Curriculum Learningcited by 47
  35. 2021Sample Efficient Linear Meta-Learning by Alternating Minimizationcited by 25
  36. 2023RetICL: Sequential Retrieval of In-Context Examples with Reinforcement Learningcited by 24
  37. 2022Determinantal Point Process Likelihoods for Sequential Recommendationcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4; 2026: 1.

5 papers.

  1. 2025Relic: Enhancing Reward Model Generalization for Low-Resource Indic Languages with Few-Shot Examplescited by 6
  2. 2025NormGenesis: Multicultural Dialogue Generation via Exemplar-Guided Social Norm Modeling and Violation Recoverycited by 2
  3. 2026MERIT: Multilingual Expert-Reward Informed Tuning for Chinese-Centric Low-Resource Machine Translationcited by 1
  4. 2025KITE: Kernelized and Information Theoretic Exemplars for In-Context Learningcited by 0
  5. 2025TRepLiNa: Layer-wise CKA+REPINA Alignment Improves Low-Resource Machine Translation in Aya-23 8Bcited by 0