English(EN) Data Efficient Sample Selection for In-Context Learning

DearICL框架通过新颖的样本选择增强LLM上下文学习

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-10 04:00

研究人员开发了DearICL，这是一个用于在大型语言模型（LLM）的上下文学习（ICL）中选择最佳演示示例的新颖框架。与静态、离线选择方法不同，DearICL将样本选择视为一个子集排序问题，采用非线性代理和间隙指数老虎机算法。这种方法可以对有效和边界示例进行细粒度分离，从而实现实例级别的子集排序。在开源LLM上的实验表明，DearICL在低样本复杂度下，相比现有的线性老虎机基线，准确率提高了8.08%至15.9%。 AI

影响通过优化演示示例选择，提高LLM对新任务的适应性，可能带来更高效、更准确的少样本学习。

排序理由这是一篇详细介绍LLM上下文学习新方法的学术论文。

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 13 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 这是一篇详细介绍LLM上下文学习新方法的学术论文。
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · V Venktesh, Cem levi, Avishek Anand · 2026-09-10 04:00

Data Efficient Sample Selection for In-Context Learning

arXiv:2609.06670v1 Announce Type: new Abstract: The In-context learning (ICL) paradigm aids large language models (LLMs) to adapt to new tasks without need for fine-tuning. However, selecting an optimal combination of demonstration examples from a large pool of example subsets is…

本文如何被排名

报道来源 [1]

Data Efficient Sample Selection for In-Context Learning

相关实体

相关话题