Do LLMs Benefit from User and Item Embeddings in Recommendation Tasks?

• URL: http://arxiv.org/abs/2601.04690v1
• Date: Thu, 08 Jan 2026 07:58:28 GMT
• Title: Do LLMs Benefit from User and Item Embeddings in Recommendation Tasks?
• Authors: Mir Rayat Imtiaz Hossain, Leo Feng, Leonid Sigal, Mohamed Osama Ahmed,
• Abstract summary: Large Language Models (LLMs) have emerged as promising recommendation systems.<n>We propose a simple yet effective solution that projects user and item embeddings, learned from collaborative filtering, into the LLM token space.<n>Preliminary results show that this design effectively leverages structured user-item interaction data, improves recommendation performance over text-only LLM baselines.
• Score: 28.468343426360708
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) have emerged as promising recommendation systems, offering novel ways to model user preferences through generative approaches. However, many existing methods often rely solely on text semantics or incorporate collaborative signals in a limited manner, typically using only user or item embeddings. These methods struggle to handle multiple item embeddings representing user history, reverting to textual semantics and neglecting richer collaborative information. In this work, we propose a simple yet effective solution that projects user and item embeddings, learned from collaborative filtering, into the LLM token space via separate lightweight projector modules. A finetuned LLM then conditions on these projected embeddings alongside textual tokens to generate recommendations. Preliminary results show that this design effectively leverages structured user-item interaction data, improves recommendation performance over text-only LLM baselines, and offers a practical path for bridging traditional recommendation systems with modern LLMs.

Related papers

• HistLLM: A Unified Framework for LLM-Based Multimodal Recommendation with User History Encoding and Compression [33.34435467588446]
  HistLLM is an innovative framework that integrates textual and visual features through a User History.<n> Module (UHEM), compressing user history interactions into a single token representation.<n>Extensive experiments demonstrate the effectiveness and efficiency of our proposed mechanism.
  arXiv  Detail & Related papers  (2025-04-14T12:01:11Z)
• Towards a Unified Paradigm: Integrating Recommendation Systems as a New Language in Large Models [33.02146794292383]
  We introduce a new concept, "Integrating Recommendation Systems as a New Language in Large Models" (RSLLM)<n>RSLLM uses a unique prompting method that combines ID-based item embeddings from conventional recommendation models with textual item features.<n>It treats users' sequential behaviors as a distinct language and aligns the ID embeddings with the LLM's input space using a projector.
  arXiv  Detail & Related papers  (2024-12-22T09:08:46Z)
• Optimizing Token Usage on Large Language Model Conversations Using the Design Structure Matrix [49.1574468325115]
  Large Language Models become ubiquitous in many sectors and tasks. There is a need to reduce token usage, overcoming challenges such as short context windows, limited output sizes, and costs associated with token intake and generation. This work brings the Design Structure Matrix from the engineering design discipline into LLM conversation optimization.
  arXiv  Detail & Related papers  (2024-10-01T14:38:36Z)
• Large Language Model Driven Recommendation [34.45328907249946]
  The advent of language-driven recommendation has unlocked the use of natural language (NL) interactions for recommendation.<n>This chapter discusses how LLMs' abilities for general NL reasoning present novel opportunities to build highly personalized RSs.
  arXiv  Detail & Related papers  (2024-08-20T15:36:24Z)
• TokenRec: Learning to Tokenize ID for LLM-based Generative Recommendation [16.93374578679005]
  TokenRec is a novel framework for tokenizing and retrieving large-scale language models (LLMs) based Recommender Systems (RecSys)<n>Our strategy, Masked Vector-Quantized (MQ) Tokenizer, quantizes the masked user/item representations learned from collaborative filtering into discrete tokens.<n>Our generative retrieval paradigm is designed to efficiently recommend top-$K$ items for users to eliminate the need for auto-regressive decoding and beam search processes.
  arXiv  Detail & Related papers  (2024-06-15T00:07:44Z)
• Improving LLMs for Recommendation with Out-Of-Vocabulary Tokens [51.584024345378005]
  We show how to effectively tokenize users and items in Large Language Models (LLMs)-based recommender systems. We emphasize the role of out-of-vocabulary (OOV) tokens in addition to the in-vocabulary ones. Our proposed framework outperforms existing state-of-the-art methods across various downstream recommendation tasks.
  arXiv  Detail & Related papers  (2024-06-12T17:59:05Z)
• Let Me Do It For You: Towards LLM Empowered Recommendation via Tool Learning [57.523454568002144]
  Large language models (LLMs) have shown capabilities in commonsense reasoning and leveraging external tools. We introduce ToolRec, a framework for LLM-empowered recommendations via tool learning. We formulate the recommendation process as a process aimed at exploring user interests in attribute granularity. We consider two types of attribute-oriented tools: rank tools and retrieval tools.
  arXiv  Detail & Related papers  (2024-05-24T00:06:54Z)
• User-LLM: Efficient LLM Contextualization with User Embeddings [23.226164112909643]
  User-LLM is a novel framework that leverages user embeddings to directly contextualize large language models with user history interactions. Our approach achieves significant efficiency gains by representing user timelines directly as embeddings, leading to substantial inference speedups of up to 78.1X.
  arXiv  Detail & Related papers  (2024-02-21T08:03:27Z)
• CoLLM: Integrating Collaborative Embeddings into Large Language Models for Recommendation [60.2700801392527]
  We introduce CoLLM, an innovative LLMRec methodology that seamlessly incorporates collaborative information into LLMs for recommendation.<n>CoLLM captures collaborative information through an external traditional model and maps it to the input token embedding space of LLM.<n>Extensive experiments validate that CoLLM adeptly integrates collaborative information into LLMs, resulting in enhanced recommendation performance.
  arXiv  Detail & Related papers  (2023-10-30T12:25:00Z)
• Recommender AI Agent: Integrating Large Language Models for Interactive Recommendations [53.76682562935373]
  We introduce an efficient framework called textbfInteRecAgent, which employs LLMs as the brain and recommender models as tools. InteRecAgent achieves satisfying performance as a conversational recommender system, outperforming general-purpose LLMs.
  arXiv  Detail & Related papers  (2023-08-31T07:36:44Z)
• LLM-Rec: Personalized Recommendation via Prompting Large Language Models [62.481065357472964]
  Large language models (LLMs) have showcased their ability to harness commonsense knowledge and reasoning. Recent advances in large language models (LLMs) have showcased their remarkable ability to harness commonsense knowledge and reasoning. This study introduces a novel approach, coined LLM-Rec, which incorporates four distinct prompting strategies of text enrichment for improving personalized text-based recommendations.
  arXiv  Detail & Related papers  (2023-07-24T18:47:38Z)
• Low-code LLM: Graphical User Interface over Large Language Models [115.08718239772107]
  This paper introduces a novel human-LLM interaction framework, Low-code LLM. It incorporates six types of simple low-code visual programming interactions to achieve more controllable and stable responses. We highlight three advantages of the low-code LLM: user-friendly interaction, controllable generation, and wide applicability.
  arXiv  Detail & Related papers  (2023-04-17T09:27:40Z)

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.