Guardado en:
Detalles Bibliográficos
Autores principales: Zeng, Min, Sun, Jingfei, Luo, Xueyou, Liu, Caiquan, Zhang, Shiqi, Xie, Li, Chen, Xiaoxin
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2509.12108
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911156209188864
author Zeng, Min
Sun, Jingfei
Luo, Xueyou
Liu, Caiquan
Zhang, Shiqi
Xie, Li
Chen, Xiaoxin
author_facet Zeng, Min
Sun, Jingfei
Luo, Xueyou
Liu, Caiquan
Zhang, Shiqi
Xie, Li
Chen, Xiaoxin
contents In natural language processing tasks, pure reinforcement learning (RL) fine-tuning methods often suffer from inefficient exploration and slow convergence; while supervised fine-tuning (SFT) methods, although efficient in training, have limited performance ceiling and less solid theoretical foundation compared to RL. To address efficiency-capability trade-off, we propose the Guess-Think-Answer (GTA) framework that combines the efficiency of SFT with the capability gains of RL in a unified training paradigm. GTA works by having the model first produce a provisional guess (optimized via cross-entropy loss), then reflect on this guess before generating the final answer, with RL rewards shaping both the final output and the format of the entire GTA structure. This hybrid approach achieves both faster convergence than pure RL and higher performance ceiling than pure SFT. To mitigate gradient conflicts between the two training signals, we employ loss masking and gradient constraints. Empirical results on four text classification benchmarks demonstrate that GTA substantially accelerates convergence while outperforming both standalone SFT and RL baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2509_12108
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GTA: Supervised-Guided Reinforcement Learning for Text Classification with Large Language Models
Zeng, Min
Sun, Jingfei
Luo, Xueyou
Liu, Caiquan
Zhang, Shiqi
Xie, Li
Chen, Xiaoxin
Computation and Language
In natural language processing tasks, pure reinforcement learning (RL) fine-tuning methods often suffer from inefficient exploration and slow convergence; while supervised fine-tuning (SFT) methods, although efficient in training, have limited performance ceiling and less solid theoretical foundation compared to RL. To address efficiency-capability trade-off, we propose the Guess-Think-Answer (GTA) framework that combines the efficiency of SFT with the capability gains of RL in a unified training paradigm. GTA works by having the model first produce a provisional guess (optimized via cross-entropy loss), then reflect on this guess before generating the final answer, with RL rewards shaping both the final output and the format of the entire GTA structure. This hybrid approach achieves both faster convergence than pure RL and higher performance ceiling than pure SFT. To mitigate gradient conflicts between the two training signals, we employ loss masking and gradient constraints. Empirical results on four text classification benchmarks demonstrate that GTA substantially accelerates convergence while outperforming both standalone SFT and RL baselines.
title GTA: Supervised-Guided Reinforcement Learning for Text Classification with Large Language Models
topic Computation and Language
url https://arxiv.org/abs/2509.12108