Effective In-Context Example Selection through Data Compression
Not on the map. Why?
Abstract (arXiv)
In-context learning has been extensively validated in large language models. However, the mechanism and selection strategy for in-context example selection, which is a crucial ingredient in this approach, lacks systematic and in-depth research. In this paper, we propose a data compression approach to the selection of in-context examples. We introduce a two-stage method that can effectively choose relevant examples and retain sufficient information about the training dataset within the in-context examples. Our method shows a significant improvement of an average of 5.90% across five different real-world datasets using four language models.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 23 of its 33 references that are in the map. First posted on arXiv 19 May 2024.
Builds on
23 of 33 references.
References · 23
- 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,970
- 2017Understanding Black-box Predictions via Influence Functionscited by 1,714
- 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,413
- 2021What Makes Good In-Context Examples for GPT-3?cited by 1,184
- 2021Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivitycited by 1,122
- 2018Neural Network Acceptability Judgmentscited by 952
- 2022Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Taskscited by 858
- 2022What Can Transformers Learn In-Context? A Case Study of Simple Function Classescited by 700
- 2021Cross-Task Generalization via Natural Language Crowdsourcing Instructionscited by 696
- 2021Learning To Retrieve Prompts for In-Context Learningcited by 641
- 2020TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classificationcited by 414
- 2023Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selectioncited by 291
11 more
- 2023Transformers as Algorithms: Generalization and Stability in In-context Learningcited by 220
- 2022Dataset Pruning: Reducing Training Data by Examining Generalization Influencecited by 132
- 2022Ground-Truth Labels Matter: A Deeper Look into Input-Label Demonstrationscited by 116
- 2022On the Effect of Pretraining Corpora on In-context Learning by a Large-scale Language Modelcited by 78
- 2022Self-Generated In-Context Learning: Leveraging Auto-regressive Language Models as a Demonstration Generatorcited by 68
- 2020ETHOS: an Online Hate Speech Detection Datasetcited by 66
- 2023Coverage-based Example Selection for In-Context Learningcited by 58
- 2023A Short Survey of Viewing Large Language Models in Legal Aspectcited by 51
- 2024Large Language Models Enhanced Collaborative Filteringcited by 27
- 2022Improving Few-Shot Performance of Language Models via Nearest Neighbor Calibrationcited by 24
- 2024Logic Rules as Explanations for Legal Case Retrievalcited by 5
Built on by
Citing papers per year: 2024: 1; 2025: 1.
2 papers.