Tokenizing Numerical and Embedding Features for LLM RecSys

• URL: http://arxiv.org/abs/2607.10016v1
• Date: Fri, 10 Jul 2026 22:36:13 GMT
• Title: Tokenizing Numerical and Embedding Features for LLM RecSys
• Abstract summary: Large language models (LLMs) are increasingly used as backbone architectures for recommender systems.<n>We propose a soft-token fusion framework that maps numerical and embedding features into the LLM embedding space.<n>We show that interaction-based fusion is more effective than direct concatenation of heterogeneous soft tokens.
• Score: 17.301482289239285
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) are increasingly used as backbone architectures for recommender systems because of their strong sequence modeling and representation learning capabilities. However, most LLM-based recommenders operate primarily on discrete textual tokens, whereas practical recommendation pipelines also rely on continuous numerical features and dense embedding features produced by upstream feature engineering or pretrained encoders. This mismatch limits the ability of LLM-based models to exploit fine-grained non-textual signals. We propose a soft-token fusion framework that maps numerical and embedding features into the LLM embedding space, allowing heterogeneous recommendation signals to be consumed through the standard token interface. We instantiate the framework in a shared-parameter LLM-based two-tower retrieval model and introduce an interaction-based fusion module that refines embedding and numerical soft tokens before they are inserted into the final LLM input. Experiments on three Amazon recommendation benchmarks show that soft-token fusion improves retrieval performance over LLM-based baselines, and that interaction-based fusion is more effective than direct concatenation of heterogeneous soft tokens.

Related papers

• Multi-LLM Token Filtering and Routing for Sequential Recommendation [9.595389306819651]
  Large language models (LLMs) have recently shown promise in recommendation by providing rich semantic knowledge.<n>We propose MLTFR, a Multi-LLM Token Filtering and Routing framework for corpus-free sequential recommendation.<n>We show that MLTFR consistently outperforms state-of-the-art sequential recommendation baselines and existing alignment methods.
  arXiv  Detail & Related papers  (2026-04-20T12:50:21Z)
• Modular Representation Compression: Adapting LLMs for Efficient and Effective Recommendations [53.53864188270018]
  Large language models (LLMs) have advanced recommendation systems (RSs)<n>We propose MARC to explicitly control the modularity of LLMs.<n>MARC achieved a 2.82% eCPM lift in an online A/B test within a large-scale commercial search advertising scenario.
  arXiv  Detail & Related papers  (2026-04-20T12:08:58Z)
• FACE: A General Framework for Mapping Collaborative Filtering Embeddings into LLM Tokens [28.971310672971914]
  Large language models (LLMs) have been explored for integration with collaborative filtering (CF)-based recommendation systems.<n>A key challenge is that LLMs struggle to interpret the latent, non-semantic embeddings produced by CF approaches.<n>We propose FACE, a general interpretable framework that maps CF embeddings into pre-trained LLM tokens.
  arXiv  Detail & Related papers  (2025-10-17T15:19:54Z)
• When Transformers Meet Recommenders: Integrating Self-Attentive Sequential Recommendation with Fine-Tuned LLMs [0.0]
  SASRecLLM is a novel framework that integrates SASRec as a collaborative encoder with an LLM fine-tuned using Low-Rank Adaptation (LoRA)<n>Experiments on multiple datasets demonstrate that SASRecLLM achieves robust and consistent improvements over strong baselines in both cold-start and warm-start scenarios.
  arXiv  Detail & Related papers  (2025-07-08T07:26:55Z)
• Architecture is All You Need: Improving LLM Recommenders by Dropping the Text [0.40964539027092917]
  We propose a recommender model that uses the architecture of large language models (LLMs) while reducing layer count and dimensions.<n>We find that this simplified approach substantially outperforms both traditional sequential recommender models and PLM-based recommender models.
  arXiv  Detail & Related papers  (2025-06-18T19:18:49Z)
• LLM2Rec: Large Language Models Are Powerful Embedding Models for Sequential Recommendation [49.78419076215196]
  Sequential recommendation aims to predict users' future interactions by modeling collaborative filtering (CF) signals from historical behaviors of similar users or items.<n>Traditional sequential recommenders rely on ID-based embeddings, which capture CF signals through high-order co-occurrence patterns.<n>Recent advances in large language models (LLMs) have motivated text-based recommendation approaches that derive item representations from textual descriptions.<n>We argue that an ideal embedding model should seamlessly integrate CF signals with rich semantic representations to improve both in-domain and out-of-domain recommendation performance.
  arXiv  Detail & Related papers  (2025-06-16T13:27:06Z)
• Large Language Models are Good Relational Learners [55.40941576497973]
  We introduce Rel-LLM, a novel architecture that utilizes a graph neural network (GNN)- based encoder to generate structured relational prompts for large language models (LLMs)<n>Unlike traditional text-based serialization approaches, our method preserves the inherent relational structure of databases while enabling LLMs to process and reason over complex entity relationships.
  arXiv  Detail & Related papers  (2025-06-06T04:07:55Z)
• LLM-Lasso: A Robust Framework for Domain-Informed Feature Selection and Regularization [59.75242204923353]
  We introduce LLM-Lasso, a framework that leverages large language models (LLMs) to guide feature selection in Lasso regression.<n>LLMs generate penalty factors for each feature, which are converted into weights for the Lasso penalty using a simple, tunable model.<n>Features identified as more relevant by the LLM receive lower penalties, increasing their likelihood of being retained in the final model.
  arXiv  Detail & Related papers  (2025-02-15T02:55:22Z)
• Laser: Parameter-Efficient LLM Bi-Tuning for Sequential Recommendation with Collaborative Information [76.62949982303532]
  We propose a parameter-efficient Large Language Model Bi-Tuning framework for sequential recommendation with collaborative information (Laser) In our Laser, the prefix is utilized to incorporate user-item collaborative information and adapt the LLM to the recommendation task, while the suffix converts the output embeddings of the LLM from the language space to the recommendation space for the follow-up item recommendation. M-Former is a lightweight MoE-based querying transformer that uses a set of query experts to integrate diverse user-specific collaborative information encoded by frozen ID-based sequential recommender systems.
  arXiv  Detail & Related papers  (2024-09-03T04:55:03Z)
• Beyond Inter-Item Relations: Dynamic Adaption for Enhancing LLM-Based Sequential Recommendation [83.87767101732351]
  Sequential recommender systems (SRS) predict the next items that users may prefer based on user historical interaction sequences. Inspired by the rise of large language models (LLMs) in various AI applications, there is a surge of work on LLM-based SRS. We propose DARec, a sequential recommendation model built on top of coarse-grained adaption for capturing inter-item relations.
  arXiv  Detail & Related papers  (2024-08-14T10:03:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.