paper-with-me

Papers

Curriculum Demonstration Selection for In-Context Learning

2024-11-27 · Duc Anh Vu, Nguyen Tran Cong Duy, Xiaobao Wu, Hoang Minh Nhat, Du Mingzhe, Nguyen Thanh Thong, Anh Tuan Luu

Large Language Models (LLMs) have shown strong in-context learning (ICL) abilities with a few demonstrations. However, one critical challenge is how to select demonstrations to elicit the full potential of LLMs. In this paper, we propose Curriculum Demonstration Selection (CDS), a novel demonstration selection method for ICL. Instead of merely using similarity, CDS additionally partitions samples by their complexity measurements. Following curriculum learning, CDS then selects demonstrations from easy to difficult. Thus the selected demonstrations cover a wide range of difficulty levels, enabling LLMs to learn from varied complexities within the training set. Experiments demonstrate that our CDS consistently outperforms baseline methods, achieving notable improvements across nine LLMs on three benchmarks. Moreover, CDS proves especially effective in enhancing LLM performance in solving challenging problems.

📄 PDF Abstract BibTeX arXiv:2411.18126

Code (0)

등록된 구현이 없습니다.

Tasks

In-Context Learning

Similar Papers 제목 키워드 기반

Problem-Solving Logic Guided Curriculum In-Context Learning for LLMs Complex Reasoning

2025-02-21 · Xuetao Ma, Wenbin Jiang, Hua Huang

In-context learning (ICL) can significantly enhance the complex reasoning capabilities of large language models (LLMs), with the key lying in the selection and ordering of demonstration examples. Previous methods typical…

In-Context Learning

Many-Shot CoT-ICL: Making In-Context Learning Truly Learn

2026-05-13 · Tsz Ting Chung, Lemao Liu, Mo Yu, Dit-Yan Yeung arxiv

While many-shot ICL achieves remarkable performance, prior studies of its scaling behavior have mainly focused on non-reasoning tasks. In this work, we study many-shot ICL on reasoning tasks, with a particular focus on m…

Scaling Laws for Many-Shot In-Context Learning with Self-Generated Annotations

2025-03-04 · Zhengyao Gu, Henry Peng Zou, Yankai Chen, Aiwei Liu 외

The high cost of obtaining high-quality annotated data for in-context learning (ICL) has motivated the development of methods that use self-generated annotations in place of ground-truth labels. While these approaches ha…

In-Context Learning

Reverse Forward Curriculum Learning for Extreme Sample and Demonstration Efficiency in Reinforcement Learning

2024-05-06 · Stone Tao, Arth Shukla, Tse-kai Chan, Hao Su

Reinforcement learning (RL) presents a promising framework to learn policies through environment interaction, but often requires an infeasible amount of interaction data to solve complex tasks from sparse rewards. One di…

Reinforcement Learning (RL)

Learning Adaptive Dexterous Grasping from Single Demonstrations

2025-03-26 · Liangzhi Shi, Yulin Liu, Lingqi Zeng, Bo Ai 외

How can robots learn dexterous grasping skills efficiently and apply them adaptively based on user instructions? This work tackles two key challenges: efficient skill acquisition from limited human demonstrations and con…

Reinforcement Learning (RL)