Can I read More is not always better? Enhancing Many-Shot In-Context Learning with Differentiated and Reweighting Objectives on EtoBox?

More is not always better? Enhancing Many-Shot In-Context Learning with Differentiated and Reweighting Objectives by Zhang, Xiaoqing; Lv, Ang; Liu, Yuhan; Sung, Flood; Liu, Wei; Shang, Shuo; Chen, Xiuying; Yan, Rui is a scholarly article available to read on EtoBox.

What is More is not always better? Enhancing Many-Shot In-Context Learning with Differentiated and Reweighting Objectives about?

Large language models (LLMs) excel at few-shot in-context learning (ICL) without requiring parameter updates. However, as the number of ICL demonstrations increases from a few to many, performance tends to plateau and eventually decline. We identify two primary causes for this trend: the suboptimal negative log-likelihood (NLL) optimization objective and the incremental data noise. To address these issues, we introduce DrICL, a novel optimization method that enhances model performance through Differentiated Learning and advantage-based Reweighting objectives. Globally, DrICL utilizes differentiated learning to optimize the NLL objective, ensuring that many-shot performance surpasses zero-shot levels. Locally, it dynamically adjusts the weighting of many-shot demonstrations by leveraging cumulative advantages inspired by reinforcement learning, thereby improving generalization. This approach allows the model to handle varying numbers of shots effectively, mitigating the impact of noisy data. Recognizing the lack of multi-task datasets with diverse many-shot distributions, we develop the Many-Shot ICL Benchmark (ICL-50)-a large-scale benchmark of 50 tasks that cover shot numbers from

Author

Zhang, Xiaoqing; Lv, Ang; Liu, Yuhan; Sung, Flood; Liu, Wei; Shang, Shuo; Chen, Xiuying; Yan, Rui

Published

2025

Language

EN