Guardado en:
Detalles Bibliográficos
Autores principales: Qian, Jian, Sun, Miao, Zhou, Sifan, Zhao, Ziyu, Hun, Ruizhi, Chiang, Patrick
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2407.05693
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910602423697408
author Qian, Jian
Sun, Miao
Zhou, Sifan
Zhao, Ziyu
Hun, Ruizhi
Chiang, Patrick
author_facet Qian, Jian
Sun, Miao
Zhou, Sifan
Zhao, Ziyu
Hun, Ruizhi
Chiang, Patrick
contents In-context learning (ICL) leverages in-context examples as prompts for the predictions of Large Language Models (LLMs). These prompts play a crucial role in achieving strong performance. However, the selection of suitable prompts from a large pool of labeled examples often entails significant annotation costs. To address this challenge, we propose Sub-SA (Submodular Selective Annotation), a submodule-based selective annotation method. The aim of Sub-SA is to reduce annotation costs while improving the quality of in-context examples and minimizing the time consumption of the selection process. In Sub-SA, we design a submodular function that facilitates effective subset selection for annotation and demonstrates the characteristics of monotonically and submodularity from the theoretical perspective. Specifically, we propose RPR (Reward and Penalty Regularization) to better balance the diversity and representativeness of the unlabeled dataset attributed to a reward term and a penalty term, respectively. Consequently, the selection for annotations can be effectively addressed with a simple yet effective greedy search algorithm based on the submodular function. Finally, we apply the similarity prompt retrieval to get the examples for ICL.
format Preprint
id arxiv_https___arxiv_org_abs_2407_05693
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Sub-SA: Strengthen In-context Learning via Submodular Selective Annotation
Qian, Jian
Sun, Miao
Zhou, Sifan
Zhao, Ziyu
Hun, Ruizhi
Chiang, Patrick
Machine Learning
Artificial Intelligence
Computation and Language
In-context learning (ICL) leverages in-context examples as prompts for the predictions of Large Language Models (LLMs). These prompts play a crucial role in achieving strong performance. However, the selection of suitable prompts from a large pool of labeled examples often entails significant annotation costs. To address this challenge, we propose Sub-SA (Submodular Selective Annotation), a submodule-based selective annotation method. The aim of Sub-SA is to reduce annotation costs while improving the quality of in-context examples and minimizing the time consumption of the selection process. In Sub-SA, we design a submodular function that facilitates effective subset selection for annotation and demonstrates the characteristics of monotonically and submodularity from the theoretical perspective. Specifically, we propose RPR (Reward and Penalty Regularization) to better balance the diversity and representativeness of the unlabeled dataset attributed to a reward term and a penalty term, respectively. Consequently, the selection for annotations can be effectively addressed with a simple yet effective greedy search algorithm based on the submodular function. Finally, we apply the similarity prompt retrieval to get the examples for ICL.
title Sub-SA: Strengthen In-context Learning via Submodular Selective Annotation
topic Machine Learning
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2407.05693