@inproceedings{li-etal-2026-towards-faithful,
    title = "Towards Faithful Industrial {RAG}: A Reinforced Co-adaptation Framework for Advertising {QA}",
    author = "Li, Wenwei  and
      Xu, Ming  and
      Xia, Tianle  and
      Hu, Lingxiang  and
      Sun, Yiding  and
      Shang, Linfang  and
      Liu, Liqun  and
      Shu, Peng  and
      Yu, Huan  and
      Jiang, Jie",
    editor = "Li, Yunyao  and
      Rehm, Georg  and
      Tu, Mei",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-industry.42/",
    pages = "604--617",
    ISBN = "979-8-89176-394-4",
    abstract = "Industrial advertising question answering (QA) is a high-stakes task in which hallucinated content, particularly fabricated URLs, can lead to financial loss, compliance violations, and legal risk. Although Retrieval-Augmented Generation (RAG) is widely adopted, deploying it in production remains challenging because industrial knowledge is inherently relational, frequently updated, and insufficiently aligned with generation objectives. We propose a reinforced co-adaptation framework that jointly optimizes retrieval and generation through two components: (1) Graph-aware Retrieval (GraphRAG), which models entity-relation structure over a high-citation knowledge subgraph for multi-hop, domain-specific evidence selection; and (2) evidence-constrained reinforcement learning via Group Relative Policy Optimization (GRPO) with multi-dimensional rewards covering faithfulness, style compliance, safety, and URL validity. Experiments on an internal advertising QA dataset show consistent gains across expert-judged dimensions including accuracy, completeness, and safety, while reducing the hallucination rate by 72{\%}. A two-week online A/B test demonstrates a 28.6{\%} increase in like rate, a 46.2{\%} decrease in dislike rate, and a 92.7{\%} reduction in URL hallucination. The system has been running in production for over half a year and has served millions of QA interactions."
}