@inproceedings{bao-etal-2025-exploring,
    title = "Exploring Hybrid Sampling Inference for Aspect-based Sentiment Analysis",
    author = "Bao, Xiaoyi  and
      Qiang, Minjie  and
      Gu, Jinghang  and
      Wang, Zhongqing  and
      Huang, Chu-Ren",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Ingest-2025-COMPUTEL/2025.findings-naacl.236/",
    pages = "4199--4210",
    ISBN = "979-8-89176-195-7",
    abstract = "As the training of large language models (LLMs) will encounter high computational costs, massive works are now focusing on inference. Their methods can be generally summarised as re-sampling the target multiple times and performing a vote upon the outputs. Despite bringing significant performance improvements, it is a high-cost method that requires multiple sampling with the preset size. In this paper, we propose a simple yet efficient inference strategies named {\_}{\_}Hybrid Sampling{\_}{\_} that combining both multiple and single sampling to greatly reduce the cost of multiple sampling without sacrificing performance. {\_}{\_}Hybrid Sampling{\_}{\_} could dynamically choose the essential part of generated sequence for multiple sampling and proceed the rest with single sampling, achieving a performance-cost balance. Extensive experiments in several benchmarks underscore the robustness and effectiveness of our proposed Hybrid Sampling and more importantly, it is much faster."
}