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

ACL ARR 2026 January Submission2312 Authors

Keywords: LLM-based Recommendation, Retrieval-based, Constrained Generation, Item tokenizer

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://anonymous.4open.science/r/RecLM-cgen.

Paper Type: Long

Research Area: NLP Applications

Research Area Keywords: financial/business NLP

Contribution Types: NLP engineering experiment

Languages Studied: English

Submission Number: 2312