Grounded Token Initialization for New Vocabulary in LMs for Generative Recommendation

[2604.02324] Grounded Token Initialization for New Vocabulary in LMs for Generative Recommendation Skip to main content Search Submit Donate Log in Computer Science > Computation and Language arXiv:2604.02324 (cs) [Submitted on 2 Apr 2026 ( v1 ), last revised 27 Aug 2026 (this version, v2)] Title: Grounded Token Initialization for New Vocabulary in LMs for Generative Recommendation Authors: Daiwei Chen , Zhoutong Fu , Chengming Jiang , Haichao Zhang , Ran Zhou , Tan Wang , Chunnan Yao , Guoyao Li , Rui Cai , Yihan Cao , Ruijie Jiang , Fedor Borisyuk , Jianqiang Shen , Jingwei Wu , Ramya Korlakai Vinayak View PDF HTML (experimental) Abstract: Language models (LMs) are increasingly extended with new learnable vocabulary tokens for domain-specific tasks, such as Semantic-ID tokens in generative recommendation. The standard practice initializes these new tokens as the mean of existing vocabulary embeddings, then relies on supervised fine-tuning to learn their representations. We present a systematic analysis of this strategy: through spectral and geometric diagnostics, we show that mean initialization collapses all new tokens into a degenerate subspace, erasing inter-token distinctions that subsequent fine-tuning struggles to fully recover. These findings suggest that \emph{token initialization} is a key bottleneck when extending LMs with new vocabularies. Motivated by this diagnosis, we propose the \emph{Grounded Token Initialization Hypothesis}: linguistically grounding novel tokens in the pretrained embedding space before fine-tuning better enables the model to leverage its general-purpose knowledge for novel-token domains. We operationalize this hypothesis as GTI (Grounded Token Initialization), a lightweight grounding stage that, prior to fine-tuning, maps new tokens to distinct, semantically meaningful locations in the pretrained embedding space using only paired linguistic supervision. Despite its simplicity, GTI outperforms both mean initialization and existing auxiliary-task adaptation methods in the majority of evaluation settings across multiple generative recommendation benchmarks, including industry-scale and public datasets. Further analyses show that grounded embeddings produce richer inter-token structure that persists through fine-tuning, corroborating the hypothesis that initialization quality is a key bottleneck in vocabulary extension. Subjects: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG) Cite as: arXiv:2604.02324 [cs.CL] (or arXiv:2604.02324v2 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2604.02324 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Daiwei Chen [ view email ] [v1] Thu, 2 Apr 2026 17:59:19 UTC (11,179 KB) [v2] Thu, 27 Aug 2026 05:44:08 UTC (11,170 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.CL < prev | next > new | recent | 2026-04 Change to browse by: cs cs.AI cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Modeling Behavioral Intensity and Transitions for Generative Recommendation#138941
• Adaptive Semantic Capacity Allocation for Parallel Generative Recommendation#441847
• Grounded Token Initialization for New Vocabulary in LMs for Generative Recommendation#674350
• Generative Grammar#470252
• MERGE: Multi-LLM Ensemble for Retrieval via Generative Enrichment#1144875