@inproceedings{li-etal-2025-reflectevo,
    title = "{R}eflect{E}vo: Improving Meta Introspection of Small {LLM}s by Learning Self-Reflection",
    author = "Li, Jiaqi  and
      Dong, Xinyi  and
      Liu, Yang  and
      Yang, Zhizhuo  and
      Wang, Quansen  and
      Wang, Xiaobo  and
      Zhu, Song-Chun  and
      Jia, Zixia  and
      Zheng, Zilong",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.findings-acl.871/",
    pages = "16948--16966",
    ISBN = "979-8-89176-256-5",
    abstract = "We present a novel pipeline, ReflectEvo, to demonstrate that small language models (SLMs) can enhance meta introspection through reflection learning. This process iteratively generates self-reflection for self-training, fostering a continuous and self-evolving process. Leveraging this pipeline, we construct ReflectEvo-460k, a large-scale, comprehensive, self-generated reflection dataset with broadened instructions and diverse multi-domain tasks. Building upon this dataset, we demonstrate the effectiveness of reflection learning to improve SLMs' reasoning abilities using SFT and DPO with remarkable performance, substantially boosting Llama-3 from 52.4{\%} to 71.2{\%} and Mistral from 44.4{\%} to 71.1{\%}. It validates that ReflectEvo can rival or even surpass the reasoning capability of the three prominent open-sourced models on BIG-bench without distillation from superior models or fine-grained human annotation. We further conduct a deeper analysis of the high quality of self-generated reflections and their impact on error localization and correction. Our work highlights the potential of continuously enhancing the reasoning performance of SLMs through iterative reflection learning in the long run."
}