paper-with-me

Papers

In-Context Learning Demonstration Selection via Influence Analysis

2024-02-19 · Vinay M. S., Minh-Hao Van, Xintao Wu

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.

📄 PDF Abstract BibTeX arXiv:2402.11750

Code (1)

tizzzzy/demonstration_selection_overview pytorch

Tasks

Few-Shot LearningIn-Context Learning

Similar Papers 제목 키워드 기반

DemoShapley: Valuation of Demonstrations for In-Context Learning

2024-10-10 · Shan Xie, Man Luo, Chadly Daniel Stern, Mengnan Du 외

Large language models (LLMs) leveraging in-context learning (ICL) have set new benchmarks in few-shot learning across various tasks without needing task-specific fine-tuning. However, extensive research has demonstrated …

FairnessFew-Shot LearningIn-Context Learning

Unraveling Indirect In-Context Learning Using Influence Functions

2025-01-01 · Hadi Askari, Shivanshu Gupta, Terry Tong, Fei Wang 외

This work introduces a novel paradigm for generalized In-Context Learning (ICL), termed Indirect In-Context Learning. In Indirect ICL, we explore demonstration selection strategies tailored for two distinct real-world sc…

In-Context LearningInformativenessMMLUStrategyQA

Learn to Select: Exploring Label Distribution Divergence for In-Context Demonstration Selection in Text Classification

2025-11-10 · Ye Jiang, Taihang Wang, Youzheng Liu, Yimin Wang 외 arxiv

In-context learning (ICL) for text classification, which uses a few input-label demonstrations to describe a task, has demonstrated impressive performance on large language models (LLMs). However, the selection of in-con…

Semantic SimilarityText Classification

"Whose Side Are You On?" Estimating Ideology of Political and News Content Using Large Language Models and Few-shot Demonstration Selection

2025-03-23 · Muhammad Haroon, Magdalena Wojcieszak, Anshuman Chhabra

The rapid growth of social media platforms has led to concerns about radicalization, filter bubbles, and content bias. Existing approaches to classifying ideology are limited in that they require extensive human effort, …

ArticlesIn-Context Learning

Factors affecting the in-context learning abilities of LLMs for dialogue state tracking

2025-06-10 · Pradyoth Hegde, Santosh Kesiraju, Jan Švec, Šimon Sedláček 외

This study explores the application of in-context learning (ICL) to the dialogue state tracking (DST) problem and investigates the factors that influence its effectiveness. We use a sentence embedding based k-nearest nei…

Dialogue State TrackingIn-Context LearningSentenceSentence Embedding+1