← Back to all news
arXiv Machine Learning By Donald Loveland, Liam Collins, Bhuvesh Kumar, Danai Koutra, Neil Shah

Preserving Item Semantics for Free: Rethinking Token Initialization in LLM-Based Generative Recommendation

Read the original on arXiv Machine Learning →

arXiv:2608. 07816v1 Announce Type: cross Abstract: Recent advances in generative recommendation (GR) leverage large language models (LLMs) as recommender backbones, enabling LLMs to directly generate recommendations conditioned on item-interaction histories.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Aug 28

Grounded Token Initialization for New Vocabulary in LMs for Generative Recommendation

The paper examines how new vocabulary tokens are added to language models for generative recommendation tasks. It shows that the common practice of initializing these tokens as the mean of existing embeddings collapses them into a degenerate subspace, hindering fine‑tuning. The authors propose Grounded Token Initialization (GTI), which places new tokens at semantically meaningful positions in the pretrained embedding space using linguistic supervision, and demonstrate that GTI outperforms mean initialization and other adaptation methods across several benchmarks.

By 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
llmsragfine-tuningbenchmarks
More like this →
arXiv AI
Jun 8

Understanding Generative Recommendation with Semantic IDs from a Model-scaling View

arXiv:2509. 25522v3 Announce Type: replace Abstract: Recent advancements in generative models have allowed the emergence of a promising paradigm for recommender systems (RS), known as Generative Recommendation (GR), which tries to unify rich item semantics and collaborative filtering signals.

By Jingzhe Liu, Liam Collins, Jiliang Tang, Tong Zhao, Neil Shah, Clark Mingxuan Ju
llmsragnlpefficiency
More like this →
arXiv AI
Jun 9

TRACER: Token ReAssignment for Concept ERasure in Generative Recommendation

arXiv:2606. 07688v1 Announce Type: cross Abstract: Generative recommendation formulates next-item prediction as autoregressive generation over semantic ID (SID) sequences derived from users' historical interactions, making modern recommender systems structurally similar to large language models (LLMs).

By Ziheng Chen, Jiali Cheng, Zezhong Fan, Hadi Amiri, Diyuan Wu, Gabriele Tolomei, Yang Zhang
llmssafety
More like this →