The value of text classification's future research has encountered challenges and uncertainties, due to the extraordinary efficacy demonstrated by large language models (LLMs) across numerous downstream NLP tasks. In this era of open-ended language modeling, where task boundaries are gradually fading, an urgent question emerges: have we made significant advances in text classification under the full benefit of LLMs? To answer this question, we propose RGPT, an adaptive boosting framework tailored to produce a specialized text classification LLM by recurrently ensembling a pool of strong base learners. The base learners are constructed by adaptively adjusting the distribution of training samples and iteratively fine-tuning LLMs with them. Such base learners are then ensembled to be a specialized text classification LLM, by recurrently incorporating the historical predictions from the previous learners. Through a comprehensive empirical comparison, we show that RGPT significantly outperforms 8 SOTA PLMs and 7 SOTA LLMs on four benchmarks by 1.36% on average. Further evaluation experiments show a clear surpassing of RGPT over human classification.

翻译：摘要：由于大语言模型（LLMs）在众多下游自然语言处理任务中展现出非凡的功效，文本分类未来研究的价值面临着挑战与不确定性。在这个任务边界逐渐模糊的开放式语言建模时代，一个紧迫的问题浮现：在大语言模型完全受益的情况下，我们在文本分类方面是否取得了显著进展？为解答这一问题，我们提出RGPT，一种自适应增强框架，旨在通过循环集成一组强大的基学习器来生成专用的文本分类大语言模型。这些基学习器通过自适应调整训练样本分布并迭代微调大语言模型构建而成。随后，通过循环融合先前学习器的历史预测结果，将这些基学习器集成为一个专用的文本分类大语言模型。通过全面的实证比较，我们证明RGPT在四个基准测试上平均以1.36%的优势显著优于8个最先进的预训练语言模型和7个最先进的大语言模型。进一步的评估实验显示，RGPT在性能上明确超越了人类分类水平。