Lune

ACL Findings2026

Eliminating Out-of-Domain Recommendations in LLM-based Recommender Systems: A Unified View

Hao Liao, Jiwei Zhang, Jianxun Lian, Wensheng Lu, Mingqi Wu, Shuo Wang, Yong Zhang, Yitian Huang, Mingyang Zhou, Rui Mao

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.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Adapting Large Language Models by Integrating Collaborative Semantics for Recommendation cites Autoregressive Image Generation using Residual Quantization
  • Adapting Large Language Models by Integrating Collaborative Semantics for Recommendation cites Collaborative Large Language Model for Recommender Systems
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. CRAMER: Control via Request-Aware Masking for Editing RecommendersZhiyuan Su, Naihe Feng, Zhen (Luther) Qin, Ga WuICML 2026

Builds on7

  1. M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge DistillationJianlyu Chen, Shitao Xiao, Peitian Zhang, Kun Luo et al.ACL Findings 2024 · 762 citations
  2. Autoregressive Image Generation using Residual QuantizationDoyup Lee, Chiheon Kim, Saehoon Kim, Minsu Cho et al.CVPR 2022 · 184 citations
  3. Collaborative Large Language Model for Recommender SystemsYaochen Zhu, Liang Wu, Qi Guo, Liangjie Hong et al.WWW 2024 · 150 citations
  4. Adapting Large Language Models by Integrating Collaborative Semantics for RecommendationBowen Zheng, Yupeng Hou, Hongyu Lu, Yu Chen et al.ICDE 2024 · 132 citations
  5. IDGenRec: LLM-RecSys Alignment with Textual ID LearningJuntao Tan, Shuyuan Xu, Wenyue Hua, Yingqiang Ge et al.SIGIR 2024 · 45 citations

Related papers

  1. Bridging Items and Language: A Transition Paradigm for Large Language Model-Based RecommendationXinyu Lin, Wenjie Wang, Yongqi Li, Fuli Feng et al.KDD 2024 · 27 citations
  2. Logit Space Constrained Fine-Tuning for Mitigating Hallucinations in LLM-Based Recommender SystemsJianfeng Deng, Qingfeng Chen, Debo Cheng, Jiuyong Li et al.EMNLP 2025 · 1 citation
  3. A Unified Model for Personalization: Language-Steerable Generative Recommendation, Search, and User UnderstandingMarco De Nadai, Edoardo D'Amico, Max Lefarov, Alexandre Tamborrino et al.KDD 2026
  4. Beyond Utility: Evaluating LLM as RecommenderChumeng Jiang, Jiayin Wang, Weizhi Ma, Charles L. A. Clarke et al.WWW 2025 · 22 citations
  5. MGFRec: Towards Reinforced Reasoning Recommendation with Multiple Groundings and FeedbackShihao Cai, Chongming Gao, Haoyan Liu, Wentao Shi et al.KDD 2026
Dusk over the sea between two cliffs drawn in fine vertical lines