@inproceedings{liao-etal-2026-eliminating,
    title = "Eliminating Out-of-Domain Recommendations in {LLM}-based Recommender Systems: A Unified View",
    author = "Liao, Hao  and
      Zhang, Jiwei  and
      Lian, Jianxun  and
      Lu, Wensheng  and
      Wu, Mingqi  and
      Shuowangg  and
      Zhang, Yong  and
      Huang, Yitian  and
      Zhou, Mingyang  and
      Mao, Rui",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.310/",
    pages = "6251--6271",
    ISBN = "979-8-89176-395-1",
    abstract = "Recommender systems based on Large Language Models (LLMs) are often plagued by hallucinations of out-of-domain (OOD) items. To address this, we propose RecLM, a unified framework that bridges the gap between retrieval and generation by instantiating three grounding paradigms under a single architecture: embedding-based retrieval, constrained generation over rewritten item titles, and discrete item-tokenizer generation. Using the same backbone LLM and prompts, we systematically compare these three views on public benchmarks. RecLM strictly eradicates OOD recommendations (OOD@10 = 0) across all variants, and the constrained generation variants RecLM-cgen and RecLM-token achieve overall state-of-the-art accuracy compared to both strong ID-based and LLM-based baselines. Our unified view provides a systematic basis for comparing three distinct paradigms to reduce item hallucinations, offering a practical framework to facilitate the application of LLMs to recommendation tasks. Source code is at https://github.com/microsoft/RecAI."
}