Paper
Trie-Aware Transformers for Generative Recommendation
Authors
Zhenxiang Xu, Jiawei Chen, Sirui Chen, Yong He, Jieyu Yang, Chuan Yuan, Ke Ding, Can Wang
Abstract
Generative recommendation (GR) aligns with advances in generative AI by casting next-item prediction as token-level generation rather than score-based ranking. Most GR methods adopt a two-stage pipeline: (i) \textit{item tokenization}, which maps each item to a sequence of discrete, hierarchically organized tokens; and (ii) \textit{autoregressive generation}, which predicts the next item's tokens conditioned on the tokens of user's interaction history. Although hierarchical tokenization induces a prefix tree (trie) over items, standard autoregressive modeling with conventional Transformers often flattens item tokens into a linear stream and overlooks the underlying topology. To address this, we propose TrieRec, a trie-aware generative recommendation method that augments Transformers with structural inductive biases via two positional encodings. First, a \textit{trie-aware absolute positional encoding} aggregates a token's (node's) local structural context (\eg depth, ancestors, and descendants) into the token representation. Second, a \textit{topology-aware relative positional encoding} injects pairwise structural relations into self-attention to capture topology-induced semantic relatedness. TrieRec is also model-agnostic, efficient, and hyperparameter-free. In our experiments, we implement TrieRec within three representative GR backbones, achieving notably improvements of 8.83\% on average across four real-world datasets.
Metadata
Related papers
Vibe Coding XR: Accelerating AI + XR Prototyping with XR Blocks and Gemini
Ruofei Du, Benjamin Hersh, David Li, Nels Numan, Xun Qian, Yanhe Chen, Zhongy... • 2026-03-25
Comparing Developer and LLM Biases in Code Evaluation
Aditya Mittal, Ryan Shar, Zichu Wu, Shyam Agarwal, Tongshuang Wu, Chris Donah... • 2026-03-25
The Stochastic Gap: A Markovian Framework for Pre-Deployment Reliability and Oversight-Cost Auditing in Agentic Artificial Intelligence
Biplab Pal, Santanu Bhattacharya • 2026-03-25
Retrieval Improvements Do Not Guarantee Better Answers: A Study of RAG for AI Policy QA
Saahil Mathur, Ryan David Rittner, Vedant Ajit Thakur, Daniel Stuart Schiff, ... • 2026-03-25
MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination
Zhuo Li, Yupeng Zhang, Pengyu Cheng, Jiajun Song, Mengyu Zhou, Hao Li, Shujie... • 2026-03-25
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2602.21677v1</id>\n <title>Trie-Aware Transformers for Generative Recommendation</title>\n <updated>2026-02-25T08:25:16Z</updated>\n <link href='https://arxiv.org/abs/2602.21677v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2602.21677v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>Generative recommendation (GR) aligns with advances in generative AI by casting next-item prediction as token-level generation rather than score-based ranking. Most GR methods adopt a two-stage pipeline: (i) \\textit{item tokenization}, which maps each item to a sequence of discrete, hierarchically organized tokens; and (ii) \\textit{autoregressive generation}, which predicts the next item's tokens conditioned on the tokens of user's interaction history. Although hierarchical tokenization induces a prefix tree (trie) over items, standard autoregressive modeling with conventional Transformers often flattens item tokens into a linear stream and overlooks the underlying topology.\n To address this, we propose TrieRec, a trie-aware generative recommendation method that augments Transformers with structural inductive biases via two positional encodings. First, a \\textit{trie-aware absolute positional encoding} aggregates a token's (node's) local structural context (\\eg depth, ancestors, and descendants) into the token representation. Second, a \\textit{topology-aware relative positional encoding} injects pairwise structural relations into self-attention to capture topology-induced semantic relatedness. TrieRec is also model-agnostic, efficient, and hyperparameter-free. In our experiments, we implement TrieRec within three representative GR backbones, achieving notably improvements of 8.83\\% on average across four real-world datasets.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.IR'/>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n <published>2026-02-25T08:25:16Z</published>\n <arxiv:primary_category term='cs.IR'/>\n <author>\n <name>Zhenxiang Xu</name>\n </author>\n <author>\n <name>Jiawei Chen</name>\n </author>\n <author>\n <name>Sirui Chen</name>\n </author>\n <author>\n <name>Yong He</name>\n </author>\n <author>\n <name>Jieyu Yang</name>\n </author>\n <author>\n <name>Chuan Yuan</name>\n </author>\n <author>\n <name>Ke Ding</name>\n </author>\n <author>\n <name>Can Wang</name>\n </author>\n </entry>"
}