Towards End-to-End Alignment of User Satisfaction via Questionnaire in Video Recommendation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914285807992832 |
|---|---|
| author | Li, Na Yu, Jiaqi Xie, Minzhi He, Tiantian Xu, Xiaoxiao Wang, Zixiu Hu, Lantao Liu, Yongqi Li, Han Zhan, Kaiqiao Gai, Kun |
| author_facet | Li, Na Yu, Jiaqi Xie, Minzhi He, Tiantian Xu, Xiaoxiao Wang, Zixiu Hu, Lantao Liu, Yongqi Li, Han Zhan, Kaiqiao Gai, Kun |
| contents | Short-video recommender systems typically optimize ranking models using dense user behavioral signals, such as clicks and watch time. However, these signals are only indirect proxies of user satisfaction and often suffer from noise and bias. Recently, explicit satisfaction feedback collected through questionnaires has emerged as a high-quality direct alignment supervision, but is extremely sparse and easily overwhelmed by abundant behavioral data, making it difficult to incorporate into online recommendation models. To address these challenges, we propose a novel framework which is towards End-to-End Alignment of user Satisfaction via Questionaire, named EASQ, to enable real-time alignment of ranking models with true user satisfaction. Specifically, we first construct an independent parameter pathway for sparse questionnaire signals by combining a multi-task architecture and a lightweight LoRA module. The multi-task design separates sparse satisfaction supervision from dense behavioral signals, preventing the former from being overwhelmed. The LoRA module pre-inject these preferences in a parameter-isolated manner, ensuring stability in the backbone while optimizing user satisfaction. Furthermore, we employ a DPO-based optimization objective tailored for online learning, which aligns the main model outputs with sparse satisfaction signals in real time. This design enables end-to-end online learning, allowing the model to continuously adapt to new questionnaire feedback while maintaining the stability and effectiveness of the backbone. Extensive offline experiments and large-scale online A/B tests demonstrate that EASQ consistently improves user satisfaction metrics across multiple scenarios. EASQ has been successfully deployed in a production short-video recommendation system, delivering significant and stable business gains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_20215 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Towards End-to-End Alignment of User Satisfaction via Questionnaire in Video Recommendation Li, Na Yu, Jiaqi Xie, Minzhi He, Tiantian Xu, Xiaoxiao Wang, Zixiu Hu, Lantao Liu, Yongqi Li, Han Zhan, Kaiqiao Gai, Kun Information Retrieval Short-video recommender systems typically optimize ranking models using dense user behavioral signals, such as clicks and watch time. However, these signals are only indirect proxies of user satisfaction and often suffer from noise and bias. Recently, explicit satisfaction feedback collected through questionnaires has emerged as a high-quality direct alignment supervision, but is extremely sparse and easily overwhelmed by abundant behavioral data, making it difficult to incorporate into online recommendation models. To address these challenges, we propose a novel framework which is towards End-to-End Alignment of user Satisfaction via Questionaire, named EASQ, to enable real-time alignment of ranking models with true user satisfaction. Specifically, we first construct an independent parameter pathway for sparse questionnaire signals by combining a multi-task architecture and a lightweight LoRA module. The multi-task design separates sparse satisfaction supervision from dense behavioral signals, preventing the former from being overwhelmed. The LoRA module pre-inject these preferences in a parameter-isolated manner, ensuring stability in the backbone while optimizing user satisfaction. Furthermore, we employ a DPO-based optimization objective tailored for online learning, which aligns the main model outputs with sparse satisfaction signals in real time. This design enables end-to-end online learning, allowing the model to continuously adapt to new questionnaire feedback while maintaining the stability and effectiveness of the backbone. Extensive offline experiments and large-scale online A/B tests demonstrate that EASQ consistently improves user satisfaction metrics across multiple scenarios. EASQ has been successfully deployed in a production short-video recommendation system, delivering significant and stable business gains. |
| title | Towards End-to-End Alignment of User Satisfaction via Questionnaire in Video Recommendation |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2601.20215 |