Litcius/Paper detail

Pushing The Limit of LLM Capacity for Text Classification

Yazhou Zhang, Mengyao Wang, Qiuchi Li, Prayag Tiwari, Jing Qin

202528 citationsDOIOpen Access PDF

Abstract

In this era of open-ended language modeling, where task boundaries are gradually fading, an urgent question emerges: have we made significant progress in text classification with 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 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 state-of-the-art (SoTA) PLMs and 7 SoTA LLMs on four benchmarks by 2.90% on average. Further evaluation experiments reveal a clear superiority of RGPT over average human classification performance.

Topics & Concepts

Limit (mathematics)Computer scienceMathematicsMathematical analysisMathematics, Computing, and Information ProcessingNatural Language Processing TechniquesLibrary Science and Information Systems