Salvato in:
| Autori principali: | , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2605.17267 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916020350877696 |
|---|---|
| author | Zhang, Yingyi Li, Junyi Wang, Yejing Zhang, Wenlin Qian, Xiaowei Zhang, Sheng Feng, Yue Wang, Yichao Liu, Yong Zhao, Xiangyu Li, Xianneng |
| author_facet | Zhang, Yingyi Li, Junyi Wang, Yejing Zhang, Wenlin Qian, Xiaowei Zhang, Sheng Feng, Yue Wang, Yichao Liu, Yong Zhao, Xiangyu Li, Xianneng |
| contents | Sequential recommendation (SR) is traditionally formulated as next-item prediction over a chronological sequence of interacted items. Although recent generative recommendation (GR) methods introduce new machinery, such as semantic IDs, autoregressive decoding, and unified token spaces, they largely inherit the same item-only modeling assumption. We argue that this design constitutes a structural bottleneck, because user decision-making is not purely behavioral: while item interactions reveal what users choose, review feedback often explain why they choose it by exposing latent evaluative factors.
Motivated by this observation, we propose Review-Augmented Generative Recommendation (RAGR), a novel GR framework that incorporates review feedback directly into the generative user sequence rather than treating reviews as auxiliary side information. Specifically, RAGR introduces a Review-Augmented User Sequence Modeling mechanism that interleaves item semantic IDs and review semantic IDs in chronological order to construct a mixed behavioral-semantic sequence, enabling review signals to participate directly in autoregressive next-token generation. To preserve the recommendation objective, we further introduce an Item-Centric Task Generation Alignment strategy based on direct preference optimization (DPO), which encourages the model to favor item tokens over review tokens at prediction positions. Experiments on three real-world datasets show that RAGR yields consistent and significant gains over strong GR backbones across all metrics. Our code and data are available at \url{https://github.com/Zhang-Yingyi/TKDE_RAGR}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_17267 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | RAGR: Review-Augmented Generative Recommendation Zhang, Yingyi Li, Junyi Wang, Yejing Zhang, Wenlin Qian, Xiaowei Zhang, Sheng Feng, Yue Wang, Yichao Liu, Yong Zhao, Xiangyu Li, Xianneng Information Retrieval Sequential recommendation (SR) is traditionally formulated as next-item prediction over a chronological sequence of interacted items. Although recent generative recommendation (GR) methods introduce new machinery, such as semantic IDs, autoregressive decoding, and unified token spaces, they largely inherit the same item-only modeling assumption. We argue that this design constitutes a structural bottleneck, because user decision-making is not purely behavioral: while item interactions reveal what users choose, review feedback often explain why they choose it by exposing latent evaluative factors. Motivated by this observation, we propose Review-Augmented Generative Recommendation (RAGR), a novel GR framework that incorporates review feedback directly into the generative user sequence rather than treating reviews as auxiliary side information. Specifically, RAGR introduces a Review-Augmented User Sequence Modeling mechanism that interleaves item semantic IDs and review semantic IDs in chronological order to construct a mixed behavioral-semantic sequence, enabling review signals to participate directly in autoregressive next-token generation. To preserve the recommendation objective, we further introduce an Item-Centric Task Generation Alignment strategy based on direct preference optimization (DPO), which encourages the model to favor item tokens over review tokens at prediction positions. Experiments on three real-world datasets show that RAGR yields consistent and significant gains over strong GR backbones across all metrics. Our code and data are available at \url{https://github.com/Zhang-Yingyi/TKDE_RAGR}. |
| title | RAGR: Review-Augmented Generative Recommendation |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2605.17267 |