用大模型自动生成文本解释，能有效提升分类性能。
Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Study
- 用多个大模型自动生成类人解释
- 自动生成解释可媲美人工标注效果
- 适合需要大规模可解释数据的研究者
在快速发展的可解释自然语言处理领域，文本解释（即类人推理）对于解释模型预测和丰富带有可解释标签的数据集至关重要。传统方法依赖人工标注，成本高、耗时长且难以扩展。本文提出一个自动化框架，利用多个先进的大语言模型（LLMs）生成高质量文本解释。我们通过一套全面的自然语言生成（NLG）指标严格评估这些自动生成解释的质量。此外，我们在两个不同的基准数据集上，研究了这些解释对预训练语言模型（PLMs）和大语言模型（LLMs）在自然语言推理任务中的下游影响。实验表明，与人工标注解释相比，自动生成的解释在提升模型性能方面表现出高度竞争力。研究结果强调了基于大模型的自动化文本解释生成在扩展NLP数据集和提升模型性能方面的广阔前景。
原文摘要 · Abstract (English)
In the rapidly evolving field of Explainable Natural Language Processing (NLP), textual explanations, i.e., human-like rationales, are pivotal for explaining model predictions and enriching datasets with interpretable labels. Traditional approaches rely on human annotation, which is costly, labor-intensive, and impedes scalability. In this work, we present an automated framework that leverages multiple state-of-the-art large language models (LLMs) to generate high-quality textual explanations. We rigorously assess the quality of these LLM-generated explanations using a comprehensive suite of Natural Language Generation (NLG) metrics. Furthermore, we investigate the downstream impact of these explanations on the performance of pre-trained language models (PLMs) and LLMs across natural language inference tasks on two diverse benchmark datasets. Our experiments demonstrate that automated explanations exhibit highly competitive effectiveness compared to human-annotated explanations in improving model performance. Our findings underscore a promising avenue for scalable, automated LLM-based textual explanation generation for extending NLP datasets and enhancing model performance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。