@inproceedings{liu-etal-2025-instruct,
    title = "Instruct-of-Reflection: Enhancing Large Language Models Iterative Reflection Capabilities via Dynamic-Meta Instruction",
    author = "Liu, Liping  and
      Zhang, Chunhong  and
      Wu, Likang  and
      Zhao, Chuang  and
      Hu, Zheng  and
      He, Ming  and
      Fan, Jianping",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Ingest-2025-COMPUTEL/2025.naacl-long.502/",
    pages = "9956--9978",
    ISBN = "979-8-89176-189-6",
    abstract = "Self-reflection for Large LanguageModels (LLMs) has gained significant attention. Existing approaches involve models iterating and improving their previous responses based on LLMs' internal reflection ability or external feedback. However, recent research has raised doubts about whether intrinsic self-correction without external feedback may even degrade performance. Based on our empirical evidence, we find that current static reflection methods may lead to redundant, drift, and stubborn issues. To mitigate this, we introduce **I**nstruct-**o**f-**R**eflec**t**ion (**IoRT**), a novel and general reflection framework that leverages dynamic-meta instruction to enhance the iterative reflection capability of LLMs. Specifically, we propose the instructor driven by the meta-thoughts and self-consistency classifier, generates various instructions, including refresh, stop, and select, to guide the next reflection iteration. Our experiments demonstrate that IoRT achieves an average improvement of 10.1{\%} over established baselines in mathematical and commonsense reasoning tasks, highlighting its efficacy and applicability. Our code is available at https://github.com/llp635/IoRT."
}