@inproceedings{qiu-etal-2025-knowledge,
    title = "Knowledge-Augmented Question Error Correction for {C}hinese Question Answer System with {Q}uestion{RAG}",
    author = "Qiu, Longpeng  and
      Li, Ting  and
      Mao, Shuai  and
      Yang, Nan  and
      Yan, Xiaohui",
    editor = "Potdar, Saloni  and
      Rojas-Barahona, Lina  and
      Montella, Sebastien",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track",
    month = nov,
    year = "2025",
    address = "Suzhou (China)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-industry.107/",
    pages = "1533--1542",
    ISBN = "979-8-89176-333-3",
    abstract = "Input errors in question-answering (QA) systems often lead to incorrect responses. Large language models (LLMs) struggle with this task, frequently failing to interpret user intent (misinterpretation) or unnecessarily altering the original question{'}s structure (over-correction).We propose QuestionRAG, a framework that tackles these problems. To address misinterpretation, it enriches the input with external knowledge (e.g., search results, related entities). To prevent over-correction, it uses reinforcement learning (RL) to align the model{'}s objective with precise correction, not just paraphrasing.Our results demonstrate that knowledge augmentation is critical for understanding faulty questions. Furthermore, RL-based alignment proves significantly more effective than traditional supervised fine-tuning (SFT), boosting the model{'}s ability to follow instructions and generalize. By integrating these two strategies, QuestionRAG unlocks the full potential of LLMs for the question correction task."
}