@inproceedings{kirtania-etal-2025-stackfeed,
    title = "{STACKFEED}: Structured Textual Actor-Critic Knowledge base editing with {FEED}back",
    author = "Kirtania, Shashank  and
      Gupta, Naman  and
      Gupta, Priyanshu  and
      Gulwani, Sumit  and
      Iyer, Arun  and
      Iyengar, Suresh Parthasarathy  and
      Radhakrishna, Arjun  and
      Rajamani, Sriram K.  and
      Soares, Gustavo",
    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.176/",
    pages = "2588--2606",
    ISBN = "979-8-89176-333-3",
    abstract = "Large Language Models (LLMs) often generate incorrect or outdated information, especially in low-resource settings or when dealing with private data. To address this, Retrieval-Augmented Generation (RAG) uses external knowledge bases (KBs), but these can also suffer from inaccuracies. We introduce STACKFEED, a novel Structured Textual Actor-Critic Knowledge base editing with Feedback approach that iteratively refines the KB based on expert feedback using a multi-actor, centralized critic reinforcement learning framework. STACKFEED defines a ReACT actor agent on each document to perform structured edits based on document-specific targeted instructions. Experimental results showcase that STACKFEED significantly improves KB quality and performance of the RAG system. We evaluate STACKFEED on low-resource programming problems, modified Python packages, and factual question-answering tasks."
}