Eliminating Out-of-Domain Recommendations in LLM-based Recommender Systems: A Unified View
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917216222445568 |
|---|---|
| author | Liao, Hao Zhang, Jiwei Lian, Jianxun Lu, Wensheng Wu, Mingqi Wang, Shuo Zhang, Yong Huang, Yitian Zhou, Mingyang Mao, Rui |
| author_facet | Liao, Hao Zhang, Jiwei Lian, Jianxun Lu, Wensheng Wu, Mingqi Wang, Shuo Zhang, Yong Huang, Yitian Zhou, Mingyang Mao, Rui |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_03336 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Eliminating Out-of-Domain Recommendations in LLM-based Recommender Systems: A Unified View Liao, Hao Zhang, Jiwei Lian, Jianxun Lu, Wensheng Wu, Mingqi Wang, Shuo Zhang, Yong Huang, Yitian Zhou, Mingyang Mao, Rui Information Retrieval Artificial Intelligence 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. |
| title | Eliminating Out-of-Domain Recommendations in LLM-based Recommender Systems: A Unified View |
| topic | Information Retrieval Artificial Intelligence |
| url | https://arxiv.org/abs/2505.03336 |