DecIF: Improving Instruction-Following through Decomposition
Tingfeng Hui, Pengyu Zhu, Bowen Ping, Ling Tang, Guanting Dong, Yaqi Zhang, Sen Su Beijing University of Posts and Telecommunications
原文摘要
We propose a novel data synthesis framework, DecIF, which automatically generates accurate and diverse instruction-following data from scratch for supervised fine-tuning (SFT) and reinforcement learning (RL), leveraging large language models (LLMs) and minimal external resources. By decomposing the data synthesis pipeline into fine-grained steps, DecIF achieves meticulous quality and diversity control over generated instruction-following data. Extensive experiments across both SFT and RL demonstrate DecIF’s strong capability to flexibly synthesize accurate instruction-following data for both paradigms compared to comprehensive baselines. Further analysis demonstrates the framework’s robustness, scalability, and computational efficiency in instruction-following data generation, while its modular design ensures straightforward implementation and reproducibility.
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表