LLM-as-Annotator: 利用LLM标注示例训练轻量模型进行方面情感元组预测
LLM-as-an-Annotator: Training Lightweight Models with LLM-Annotated Examples for Aspect Sentiment Tuple Prediction
AI总结：
本文提出LA-ABSA方法，利用LLM生成的标注示例训练轻量模型，以高效完成复杂的情感分析任务。
摘要：
针对基于方面的情感分析（ABSA）任务，训练模型需要手动标注数据，这获取成本高且耗时。本文提出LA-ABSA，一种利用大语言模型（LLM）生成的标注来微调轻量模型以处理复杂ABSA任务的新方法。我们在五个针对目标方面情感检测（TASD）和方面情感四元组预测（ASQP）的数据集上评估了我们的方法。我们的方法在低资源场景中优于先前的增强策略，并在计算资源上提供了显著的能效优势。例如，使用50个标注示例进行上下文学习（ICL）来指导未标注数据的标注，LA-ABSA在SemEval Rest16数据集上实现了ASQP的F1得分为49.85，接近ICL提示Gemma-3-27B（51.10）的性能，同时需要显著较少的计算资源。
英文摘要：
Training models for Aspect-Based Sentiment Analysis (ABSA) tasks requires manually annotated data, which is expensive and time-consuming to obtain. This paper introduces LA-ABSA, a novel approach that leverages Large Language Model (LLM)-generated annotations to fine-tune lightweight models for complex ABSA tasks. We evaluate our approach on five datasets for Target Aspect Sentiment Detection (TASD) and Aspect Sentiment Quad Prediction (ASQP). Our approach outperformed previously reported augmentation strategies and achieved competitive performance with LLM-prompting in low-resource scenarios, while providing substantial energy efficiency benefits. For example, using 50 annotated examples for in-context learning (ICL) to guide the annotation of unlabeled data, LA-ABSA achieved an F1 score of 49.85 for ASQP on the SemEval Rest16 dataset, closely matching the performance of ICL prompting with Gemma-3-27B (51.10), while requiring significantly lower computational resources.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
