@inproceedings{li-etal-2025-cot,
    title = "{C}o{T}-{RAG}: Integrating Chain of Thought and Retrieval-Augmented Generation to Enhance Reasoning in Large Language Models",
    author = "Li, Feiyang  and
      Fang, Peng  and
      Shi, Zhan  and
      Khan, Arijit  and
      Wang, Fang  and
      Wang, Weihao  and
      Zhangxin-hw  and
      Yongjian, Cui",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.168/",
    doi = "10.18653/v1/2025.findings-emnlp.168",
    pages = "3119--3171",
    ISBN = "979-8-89176-335-7",
    abstract = "Chain-of-thought (CoT) reasoning boosts large language models' (LLMs) performance on complex tasks but faces two key limitations: a lack of reliability when solely relying on LLM-generated reasoning chains and interference from natural language reasoning steps with the models' inference process, also known as the inference logic of LLMs. To address these issues, we propose CoT-RAG, a novel reasoning framework with three key designs: (i) Knowledge Graph-driven CoT Generation, featuring knowledge graphs to modulate reasoning chain generation of LLMs, thereby enhancing reasoning credibility; (ii) Learnable Knowledge Case-aware RAG, which incorporates retrieval-augmented generation (RAG) into knowledge graphs to retrieve relevant sub-cases and sub-descriptions, providing LLMs with learnable information; (iii) Pseudo-Program Prompting Execution, which promotes greater logical rigor by guiding LLMs to execute reasoning tasks as pseudo-programs. Evaluations on nine public datasets spanning three reasoning tasks reveal significant accuracy gains{---}ranging from 4.0{\%} to 44.3{\%}{--}over state-of-the-art methods. Furthermore, tests on four domain-specific datasets demonstrate exceptional accuracy and efficient execution, underscoring its practical applicability and scalability. Our code and data are available at https://github.com/hustlfy123/CoT-RAG."
}