paper-with-me

홈 › Papers

STAYKATE: Hybrid In-Context Example Selection Combining Representativeness Sampling and Retrieval-based Approach -- A Case Study on Science Domains

2024-12-28 · Chencheng Zhu, Kazutaka Shimada, Tomoki Taniguchi, Tomoko Ohkuma

Large language models (LLMs) demonstrate the ability to learn in-context, offering a potential solution for scientific information extraction, which often contends with challenges such as insufficient training data and the high cost of annotation processes. Given that the selection of in-context examples can significantly impact performance, it is crucial to design a proper method to sample the efficient ones. In this paper, we propose STAYKATE, a static-dynamic hybrid selection method that combines the principles of representativeness sampling from active learning with the prevalent retrieval-based approach. The results across three domain-specific datasets indicate that STAYKATE outperforms both the traditional supervised methods and existing selection methods. The enhancement in performance is particularly pronounced for entity types that other methods pose challenges.

📄 PDF Abstract BibTeX arXiv:2412.20043

Code (0)

등록된 구현이 없습니다.

Tasks

Active LearningRetrieval

Similar Papers 제목 키워드 기반

Learning What Helps: Task-Aligned Context Selection for Vision Tasks

2025-11-29 · Jingyu Guo, Emir Konuk, Fredrik Strand, Christos Matsoukas 외 arxiv

Humans often resolve visual uncertainty by comparing an image with relevant examples, but ViTs lack the ability to identify which examples would improve their predictions. We present Task-Aligned Context Selection (TACS)…

Medical Image ClassificationMedical Image SegmentationReinforcement Learning

Few-Shot Optimization for Sensor Data Using Large Language Models: A Case Study on Fatigue Detection

2025-05-24 · Elsen Ronando, Sozo Inoue

In this paper, we propose a novel few-shot optimization with HED-LM (Hybrid Euclidean Distance with Large Language Models) to improve example selection for sensor-based classification tasks. While few-shot prompting enab…

Activity RecognitionHuman Activity Recognition

CTQScorer: Combining Multiple Features for In-context Example Selection for Machine Translation

2023-05-23 · Aswanth Kumar, Ratish Puduppully, Raj Dabre, Anoop Kunchukuttan

Large language models have demonstrated the capability to perform on machine translation when the input is prompted with a few examples (in-context learning). Translation quality depends on various features of the select…

In-Context LearningMachine TranslationRetrievalTranslation

Going Beyond Word Matching: Syntax Improves In-context Example Selection for Machine Translation

2024-03-28 · Chenming Tang, Zhixiang Wang, Yunfang Wu

In-context learning (ICL) is the trending prompting strategy in the era of large language models (LLMs), where a few examples are demonstrated to evoke LLMs' power for a given task. How to select informative examples rem…

In-Context LearningMachine TranslationTranslation

Hybrid Neural-LLM Pipeline for Morphological Glossing in Endangered Language Documentation: A Case Study of Jungar Tuvan

2026-03-01 · Siyu Liang, Talant Mawkanuli, Gina-Anne Levow arxiv

Interlinear glossed text (IGT) creation remains a major bottleneck in linguistic documentation and fieldwork, particularly for low-resource morphologically rich languages. We present a hybrid automatic glossing pipeline …

Structured Prediction