← Back to all news
arXiv AI By Gaoming Zhang, Angqing Jiang, Jianchun Song, Kena Qi, Dayao Chen, Wei Lin, Defu Lian

Preference Shapes Relevance: Cross-component Hierarchical Semantic Alignment for Personalized Generative Retrieval

Read the original on arXiv AI →

The paper introduces CHAP, a personalized generative retrieval framework that aligns query semantics with item representations through a hierarchical semantic alignment module and models user behavior using both discrete Semantic IDs and continuous representations. It also proposes a Residual Cascading Generation mechanism to reduce inference latency by limiting the Transformer decoder to a single pass. Experiments on multiple datasets and online A/B tests show that CHAP outperforms existing methods, demonstrating its practical value.

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 AI.

Related stories

arXiv AI
Oct 28

REGER: Modeling inter-item Relations with Semantic IDs for Generative Recommendation

REGER is a unified framework that enhances generative recommendation by explicitly modeling inter-item relations through semantic pretraining, history encoding, and SID generation. It pretrains the model to generate semantic neighbors’ IDs, uses combined global and local attention to capture historical context, and introduces a hierarchical preference decomposition over the SID prefix tree. The approach also distills a discriminative teacher’s full conditional distributions to improve next-token predictions, yielding consistent performance gains on real-world datasets.

By Yuxi Huang, Silin Zhou, Chenhao Wang, Zihan Li, Gangming Guo, Pei Ke, Shen Gao, Shuo Shang
ragefficiency
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 →
Hugging Face Trending Papers
Oct 27

REGER: Modeling inter-item Relations with Semantic IDs for Generative Recommendation

REGER is a framework that enhances generative recommendation by explicitly modeling inter-item relations through semantic pretraining, refined history encoding, and SID generation. It pretrains the model to generate semantic neighbors’ IDs, uses a combination of global and local attention to capture context, and introduces a hierarchical preference decomposition that allows exact factorization of collaborative preferences. The method also distills a discriminative teacher’s full conditional distributions to improve next-token predictions, yielding consistent performance gains on real-world datasets.

ragefficiency
More like this →
arXiv AI
Oct 15

Personalized LLM Recommendation with Semantic IDs: Autoregressive Beam Search vs. Multi-Token Prediction

arXiv:2610.15864v1 Announce Type: cross Abstract: Large-scale personalization is shifting from embedding-table retrieval to LLM-based recommenders that generate the Semantic ID (SID) of the item to r...

By Sejoon Oh, Fernando Amat Gil, Evan Smothers, Dan Iter, Mark Thornburg, Dawit Mureja Argaw, Sourabh Medapati, Thea Wang, Ria Verma, Qiuling Xu, Harshit Syal, Ehsan Gholami, Moumita Bhattacharya, Ashish Rastogi
llmsragreinforcement-learningefficiency
More like this →
arXiv AI
Oct 12

Beyond Semantic IDs: Finite-Beam Reachability and Continuous-Query Generation in Generative Recommendation

The paper introduces two continuous-query paradigms—CQG‑Single and CQG‑AR—to replace the traditional finite-beam, discrete Semantic ID (SID) decoding used in generative recommendation systems. By removing the SID vocabulary and beam expansion, these methods allow every encoded item to be directly scored via dense or approximate-nearest-neighbor retrieval, thereby eliminating the reachability constraints of finite-beam decoding. Experiments show that CQG‑Single outperforms a TIGER-style baseline across all runs while using fewer parameters, and CQG‑AR performs comparably or better on several datasets, suggesting that decoupling output representation, autoregressive modeling, and retrieval budget can improve generative recommendation evaluation.

By Yu Sun, Renkai Xiang, Zuodong Xiang, Junwei Zhou, Yike Zhang, Jianxin Zhang, Zhihao Zhu, Xiaoyu Cao, Hailu Xu
benchmarks
More like this →