# Order-agnostic Identifier for Large Language Model-based Generative Recommendation

arXiv: https://arxiv.org/abs/2502.10833 · HTML: https://mlsanity.com/paper/2502.10833/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Feb 2025.

## Built on by (most cited first, 21 of 21)

- [HiD-VAE: Interpretable Generative Recommendation via Hierarchical and Disentangled Semantic IDs](https://mlsanity.com/paper/2508.04618/) (2025)
- [CoFiRec: Coarse-to-Fine Tokenization for Generative Recommendation](https://mlsanity.com/paper/2511.22707/) (2025)
- [LLaDA-Rec: Discrete Diffusion for Parallel Semantic ID Generation in Generative Recommendation](https://mlsanity.com/paper/2511.06254/) (2025)
- [Eliminating Out-of-Domain Recommendations in LLM-based Recommender Systems: A Unified View](https://mlsanity.com/paper/2505.03336/) (2025)
- [DiffGRM: Diffusion-based Generative Recommendation Model](https://mlsanity.com/paper/2510.21805/) (2025)
- [GFlowGR: Fine-tuning Generative Recommendation Frameworks with Generative Flow Networks](https://mlsanity.com/paper/2506.16114/) (2025)
- [Purely Semantic Indexing for LLM-based Generative Recommendation and Retrieval](https://mlsanity.com/paper/2509.16446/) (2025)
- [When Text-as-Vision Meets Semantic IDs in Generative Recommendation: An Empirical Study](https://mlsanity.com/paper/2601.14697/) (2026)
- [Understanding Semantic IDs: From Item Representation to Item Selection in Generative Recommendation](https://mlsanity.com/paper/2607.24995/) (2026)
- [Continual Low-Rank Adapters for LLM-based Generative Recommender Systems](https://mlsanity.com/paper/2510.25093/) (2025)
- [Masked Diffusion Generative Recommendation](https://mlsanity.com/paper/2601.19501/) (2026)
- [Verifiable Reasoning for LLM-based Generative Recommendation](https://mlsanity.com/paper/2603.07725/) (2026)
- [MMGRid: Navigating Temporal-aware and Cross-domain Generative Recommendation via Model Merging](https://mlsanity.com/paper/2601.15930/) (2026)
- [Reasoning to Rank: An End-to-End Solution for Exploiting Large Language Models for Recommendation](https://mlsanity.com/paper/2602.12530/) (2026)
- [Token-Efficient Item Representation via Images for LLM Recommender Systems](https://mlsanity.com/paper/2503.06238/) (2025)
- [Beyond Semantic Understanding: Preserving Collaborative Frequency Components in LLM-based Recommendation](https://mlsanity.com/paper/2508.10312/) (2025)
- [PRISM: Purified Representation and Integrated Semantic Modeling for Generative Sequential Recommendation](https://mlsanity.com/paper/2601.16556/) (2026)
- [VaLiDRec: Variable-Length LLM-Aligned Semantic IDs for Generative Recommendation](https://mlsanity.com/paper/2607.25209/) (2026)
- [FedCGR: Federated Cross-Domain Generative Recommendation](https://mlsanity.com/paper/2608.10929/) (2026)
- [EchoRec: Multi-Item Prediction-Empowered Generative Recommendation via Cycle-Consistent Preference Alignment](https://mlsanity.com/paper/2608.14011/) (2026)
- [Adaptive Item-based Collaborative Structures via Noise Rescheduling in Diffusion for Generative Recommendation](https://mlsanity.com/paper/2608.23400/) (2026)

## Abstract (arXiv)

Leveraging Large Language Models (LLMs) for generative recommendation has attracted significant research interest, where item tokenization is a critical step. It involves assigning item identifiers for LLMs to encode user history and generate the next item. Existing approaches leverage either token-sequence identifiers, representing items as discrete token sequences, or single-token identifiers, using ID or semantic embeddings. Token-sequence identifiers face issues such as the local optima problem in beam search and low generation efficiency due to step-by-step generation. In contrast, single-token identifiers fail to capture rich semantics or encode Collaborative Filtering (CF) information, resulting in suboptimal performance. To address these issues, we propose two fundamental principles for item identifier design: 1) integrating both CF and semantic information to fully capture multi-dimensional item information, and 2) designing order-agnostic identifiers without token dependency, mitigating the local optima issue and achieving simultaneous generation for generation efficiency. Accordingly, we introduce a novel set identifier paradigm for LLM-based generative recommendation, representing each item as a set of order-agnostic tokens. To implement this paradigm, we propose SETRec, which leverages CF and semantic tokenizers to obtain order-agnostic multi-dimensional tokens. To eliminate token dependency, SETRec uses a sparse attention mask for user history encoding and a query-guided generation mechanism for simultaneous token generation. We instantiate SETRec on T5 and Qwen (from 1.5B to 7B). Extensive experiments demonstrate its effectiveness under various scenarios (e.g., full ranking, warm- and cold-start ranking, and various item popularity groups). Moreover, results validate SETRec's superior efficiency and show promising scalability on cold-start items as model sizes increase.