Pushing The Limit of LLM Capacity for Text Classification
This work addresses the problem of improving text classification accuracy for NLP researchers and practitioners, though it appears incremental as it builds on existing LLM methods with a novel ensembling approach.
The authors tackled the challenge of advancing text classification using large language models (LLMs) by proposing RGPT, an adaptive boosting framework that ensembles fine-tuned LLMs, resulting in an average performance improvement of 1.36% over state-of-the-art models on four benchmarks and surpassing human classification.
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.