Unleashing the Native Recommendation Potential: LLM-Based Generative Recommendation via Structured Term Identifiers
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915720826191872 |
|---|---|
| author | Zhang, Zhiyang She, Junda Cai, Kuo Chen, Bo Wang, Shiyao Luo, Xinchen Luo, Qiang Tang, Ruiming Li, Han Gai, Kun Zhou, Guorui |
| author_facet | Zhang, Zhiyang She, Junda Cai, Kuo Chen, Bo Wang, Shiyao Luo, Xinchen Luo, Qiang Tang, Ruiming Li, Han Gai, Kun Zhou, Guorui |
| contents | Leveraging the vast open-world knowledge and understanding capabilities of Large Language Models (LLMs) to develop general-purpose, semantically-aware recommender systems has emerged as a pivotal research direction in generative recommendation. However, existing methods face bottlenecks in constructing item identifiers. Text-based methods introduce LLMs' vast output space, leading to hallucination, while methods based on Semantic IDs (SIDs) encounter a semantic gap between SIDs and LLMs' native vocabulary, requiring costly vocabulary expansion and alignment training. To address this, this paper introduces Term IDs (TIDs), defined as a set of semantically rich and standardized textual keywords, to serve as robust item identifiers. We propose GRLM, a novel framework centered on TIDs, employs Context-aware Term Generation to convert item's metadata into standardized TIDs and utilizes Integrative Instruction Fine-tuning to collaboratively optimize term internalization and sequential recommendation. Additionally, Elastic Identifier Grounding is designed for robust item mapping. Extensive experiments on real-world datasets demonstrate that GRLM significantly outperforms baselines across multiple scenarios, pointing a promising direction for generalizable and high-performance generative recommendation systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_06798 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Unleashing the Native Recommendation Potential: LLM-Based Generative Recommendation via Structured Term Identifiers Zhang, Zhiyang She, Junda Cai, Kuo Chen, Bo Wang, Shiyao Luo, Xinchen Luo, Qiang Tang, Ruiming Li, Han Gai, Kun Zhou, Guorui Information Retrieval Leveraging the vast open-world knowledge and understanding capabilities of Large Language Models (LLMs) to develop general-purpose, semantically-aware recommender systems has emerged as a pivotal research direction in generative recommendation. However, existing methods face bottlenecks in constructing item identifiers. Text-based methods introduce LLMs' vast output space, leading to hallucination, while methods based on Semantic IDs (SIDs) encounter a semantic gap between SIDs and LLMs' native vocabulary, requiring costly vocabulary expansion and alignment training. To address this, this paper introduces Term IDs (TIDs), defined as a set of semantically rich and standardized textual keywords, to serve as robust item identifiers. We propose GRLM, a novel framework centered on TIDs, employs Context-aware Term Generation to convert item's metadata into standardized TIDs and utilizes Integrative Instruction Fine-tuning to collaboratively optimize term internalization and sequential recommendation. Additionally, Elastic Identifier Grounding is designed for robust item mapping. Extensive experiments on real-world datasets demonstrate that GRLM significantly outperforms baselines across multiple scenarios, pointing a promising direction for generalizable and high-performance generative recommendation systems. |
| title | Unleashing the Native Recommendation Potential: LLM-Based Generative Recommendation via Structured Term Identifiers |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2601.06798 |