解决大模型推荐系统幻觉问题，统一三类防外域推荐方法
Eliminating Out-of-Domain Recommendations in LLM-based Recommender Systems: A Unified View
- 统一框架整合三种防幻觉机制：检索、约束生成、离散标记生成
- 所有变体在公开数据集上外域推荐率降至0（OOD@10=0）
- 适合想安全落地LLM推荐系统的工程师与研究者
基于大语言模型（LLMs）的推荐系统常因生成外域（OOD）物品而出现幻觉。为此，我们提出RecLM统一框架，通过同一架构实现三种接地范式：基于嵌入的检索、对重写物品标题的约束生成，以及离散物品标记器生成。使用相同骨干LLM和提示，我们在公开基准上系统比较这三种方式。RecLM在所有变体中严格消除外域推荐（OOD@10 = 0），且约束生成变体RecLM-cgen与RecLM-token在整体准确率上优于强基线（包括基于ID与基于LLM的方法）。该统一视角为三类范式提供了系统性对比基础，为减少物品幻觉提供实用框架。源码见https://github.com/microsoft/RecAI。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。