# Tokenize Once, Recommend Anywhere: Unified Item Tokenization for Multi-domain LLM-based Recommendation

arXiv: https://arxiv.org/abs/2511.12922 · HTML: https://mlsanity.com/paper/2511.12922/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in MoE for recommender systems, one of 12 directions in Mixture-of-experts.
- Builds on 28 of its 40 references that are in the map.
- First posted on arXiv 17 Nov 2025.

## Placed in

- Mixture-of-experts / [MoE for recommender systems](https://mlsanity.com/moe/moe-for-recommender-systems/)

## Builds on (most cited first, 28 of 28)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [Don't Stop Pretraining: Adapt Language Models to Domains and Tasks](https://mlsanity.com/paper/2004.10964/) (2020)
- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation](https://mlsanity.com/paper/2002.02126/) (2020)
- [BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer](https://mlsanity.com/paper/1904.06690/) (2019)
- [DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models](https://mlsanity.com/paper/2401.06066/) (2024)
- [Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)](https://mlsanity.com/paper/2203.13366/) (2022)
- [Adapting Large Language Models by Integrating Collaborative Semantics for Recommendation](https://mlsanity.com/paper/2311.09049/) (2023)
- [LLMRec: Large Language Models with Graph Augmentation for Recommendation](https://mlsanity.com/paper/2311.00423/) (2023)
- [Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approach](https://mlsanity.com/paper/2305.07001/) (2023)
- [Uncovering ChatGPT's Capabilities in Recommender Systems](https://mlsanity.com/paper/2305.02182/) (2023)
- [Representation Learning with Large Language Models for Recommendation](https://mlsanity.com/paper/2310.15950/) (2023)
- [Learnable Item Tokenization for Generative Recommendation](https://mlsanity.com/paper/2405.07314/) (2024)
- [Data-efficient Fine-tuning for LLM-based Recommendation](https://mlsanity.com/paper/2401.17197/) (2024)
- [How to Index Item IDs for Recommendation Foundation Models](https://mlsanity.com/paper/2305.06569/) (2023)
- [Self-Supervised Learning with Kernel Dependence Maximization](https://mlsanity.com/paper/2106.08320/) (2021)
- [ReLLa: Retrieval-enhanced Large Language Models for Lifelong Sequential Behavior Comprehension in Recommendation](https://mlsanity.com/paper/2308.11131/) (2023)
- [Bridging Items and Language: A Transition Paradigm for Large Language Model-Based Recommendation](https://mlsanity.com/paper/2310.06491/) (2023)
- [ClickPrompt: CTR Models are Strong Prompt Generators for Adapting Language Models to CTR Prediction](https://mlsanity.com/paper/2310.09234/) (2023)
- [DAMEX: Dataset-aware Mixture-of-Experts for visual understanding of mixture-of-datasets](https://mlsanity.com/paper/2311.04894/) (2023)
- [Adaptive Domain Interest Network for Multi-domain Recommendation](https://mlsanity.com/paper/2206.09672/) (2022)
- [Searching for Optimal Subword Tokenization in Cross-domain NER](https://mlsanity.com/paper/2206.03352/) (2022)
- [Multimodal Quantitative Language for Generative Recommendation](https://mlsanity.com/paper/2504.05314/) (2025)
- [Multi-domain Recommendation with Embedding Disentangling and Domain Alignment](https://mlsanity.com/paper/2308.05508/) (2023)

## Built on by (most cited first, 1 of 1)

- [Reasoning with Evidence, Not Merely Rationales: Verifiable Preference Proofs for LLM-Based Recommendation](https://mlsanity.com/paper/2610.02968/) (2026)

## Abstract (arXiv)

Large language model (LLM)-based recommender systems have achieved high-quality performance by bridging the discrepancy between the item space and the language space through item tokenization. However, existing item tokenization methods typically require training separate models for each item domain, limiting generalization. Moreover, the diverse distributions and semantics across item domains make it difficult to construct a unified tokenization that preserves domain-specific information. To address these challenges, we propose UniTok, a Unified item Tokenization framework that integrates our own mixture-of-experts (MoE) architecture with a series of codebooks to convert items into discrete tokens, enabling scalable tokenization while preserving semantic information across multiple item domains. Specifically, items from different domains are first projected into a unified latent space through a shared encoder. They are then routed to domain-specific experts to capture the unique semantics, while a shared expert, which is always active, encodes common knowledge transferable across domains. Additionally, to mitigate semantic imbalance across domains, we present a mutual information calibration mechanism, which guides the model towards retaining similar levels of semantic information for each domain. Comprehensive experiments on wide-ranging real-world datasets demonstrate that the proposed UniTok framework is (a) highly effective: achieving up to 51.89% improvements over strong benchmarks, (b) theoretically sound: showing the analytical validity of our architectural design and optimization; and (c) highly generalizable: demonstrating robust performance across diverse domains without requiring per-domain retraining, a capability not supported by existing baselines.