Semantic IDs for Joint Generative Search and Recommendation

• URL: http://arxiv.org/abs/2508.10478v1
• Date: Thu, 14 Aug 2025 09:28:49 GMT
• Title: Semantic IDs for Joint Generative Search and Recommendation
• Authors: Gustavo Penha, Edoardo D'Amico, Marco De Nadai, Enrico Palumbo, Alexandre Tamborrino, Ali Vardasbi, Max Lefarov, Shawn Lin, Timothy Heath, Francesco Fabbri, Hugues Bouchard,
• Abstract summary: Generative models are emerging as a unified solution for powering both recommendation and search tasks.<n>We show how to construct Semantic IDs that perform well both in search and recommendation when using a unified model.
• Score: 39.49814138519702
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Generative models powered by Large Language Models (LLMs) are emerging as a unified solution for powering both recommendation and search tasks. A key design choice in these models is how to represent items, traditionally through unique identifiers (IDs) and more recently with Semantic IDs composed of discrete codes, obtained from embeddings. While task-specific embedding models can improve performance for individual tasks, they may not generalize well in a joint setting. In this paper, we explore how to construct Semantic IDs that perform well both in search and recommendation when using a unified model. We compare a range of strategies to construct Semantic IDs, looking into task-specific and cross-tasks approaches, and also whether each task should have its own semantic ID tokens in a joint search and recommendation generative model. Our results show that using a bi-encoder model fine-tuned on both search and recommendation tasks to obtain item embeddings, followed by the construction of a unified Semantic ID space provides an effective trade-off, enabling strong performance in both tasks. We hope these findings spark follow-up work on generalisable, semantically grounded ID schemes and inform the next wave of unified generative recommender architectures.

Related papers

• The Best of the Two Worlds: Harmonizing Semantic and Hash IDs for Sequential Recommendation [51.62815306481903]
  We propose textbfname, a novel framework that harmonizes the SID and HID. Specifically, we devise a dual-branch modeling architecture that enables the model to capture both the multi-granular semantics within SID while preserving the unique collaborative identity of HID.<n>Experiments on three real-world datasets show that name balances recommendation quality for both head and tail items while surpassing the existing baselines.
  arXiv  Detail & Related papers  (2025-12-11T07:50:53Z)
• Purely Semantic Indexing for LLM-based Generative Recommendation and Retrieval [28.366331215978445]
  We propose purely semantic indexing to generate unique, semantic-preserving IDs without appending non-semantic tokens.<n>We enable unique ID assignment by relaxing the strict nearest-centroid selection and introduce two model-agnostic algorithms.
  arXiv  Detail & Related papers  (2025-09-19T21:59:55Z)
• Unifying Search and Recommendation with Dual-View Representation Learning in a Generative Paradigm [51.2624255871896]
  GenSR is a novel generative paradigm for unifying search and recommendation.<n>Our work introduces a new generative paradigm compared with previous discriminative methods.
  arXiv  Detail & Related papers  (2025-04-09T09:15:37Z)
• Unified Generative Search and Recommendation [14.317849340141919]
  We introduce GenSAR, a unified generative framework for balanced search and recommendation.<n>Our approach designs dual-purpose identifiers and tailored training strategies to incorporate complementary signals and align with task-specific objectives.<n>Experiments on both public and commercial datasets demonstrate that GenSAR effectively reduces the trade-off and achieves state-of-the-art performance on both tasks.
  arXiv  Detail & Related papers  (2025-04-08T07:03:08Z)
• Order-agnostic Identifier for Large Language Model-based Generative Recommendation [94.37662915542603]
  Items are assigned identifiers for Large Language Models (LLMs) to encode user history and generate the next item.<n>Existing approaches leverage either token-sequence identifiers, representing items as discrete token sequences, or single-token identifiers, using ID or semantic embeddings.<n>We propose SETRec, which leverages semantic tokenizers to obtain order-agnostic multi-dimensional tokens.
  arXiv  Detail & Related papers  (2025-02-15T15:25:38Z)
• Bridging Search and Recommendation in Generative Retrieval: Does One Task Help the Other? [9.215695600542249]
  Generative retrieval for search and recommendation is a promising paradigm for retrieving items. These generative systems can play a crucial role in centralizing a variety of Information Retrieval (IR) tasks in a single model. This paper investigates whether and when such a unified approach can outperform task-specific models in the IR tasks of search and recommendation.
  arXiv  Detail & Related papers  (2024-10-22T08:49:43Z)
• Generative Retrieval Meets Multi-Graded Relevance [104.75244721442756]
  We introduce a framework called GRaded Generative Retrieval (GR$2$) GR$2$ focuses on two key components: ensuring relevant and distinct identifiers, and implementing multi-graded constrained contrastive training. Experiments on datasets with both multi-graded and binary relevance demonstrate the effectiveness of GR$2$.
  arXiv  Detail & Related papers  (2024-09-27T02:55:53Z)
• CorpusLM: Towards a Unified Language Model on Corpus for Knowledge-Intensive Tasks [20.390672895839757]
  Retrieval-augmented generation (RAG) has emerged as a popular solution to enhance factual accuracy. Traditional retrieval modules often rely on large document index and disconnect with generative tasks. We propose textbfCorpusLM, a unified language model that integrates generative retrieval, closed-book generation, and RAG.
  arXiv  Detail & Related papers  (2024-02-02T06:44:22Z)
• Recommender Systems with Generative Retrieval [58.454606442670034]
  We propose a novel generative retrieval approach, where the retrieval model autoregressively decodes the identifiers of the target candidates. To that end, we create semantically meaningful of codewords to serve as a Semantic ID for each item. We show that recommender systems trained with the proposed paradigm significantly outperform the current SOTA models on various datasets.
  arXiv  Detail & Related papers  (2023-05-08T21:48:17Z)

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.