# Efficient Personalized Reranking with Semi-Autoregressive Generation and Online Knowledge Distillation

Source: [Efficient Personalized Reranking with Semi-Autoregressive Generation and Online Knowledge Distillation](<https://www.sota2.com/research/paper/69afa5692d603e6de3e438c7>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-11T05:00:04.181Z

Authors: Kai Cheng, Hao Wang, Wei Guo, Weiwen Liu, Yong Liu, Yawen Li, Enhong Chen

Published: 2026-03-07T08:37:13.000Z

## Abstract

Generative models offer a promising paradigm for the final stage reranking in multi-stage recommender systems, with the ability to capture inter-item dependencies within reranked lists. However, their practical deployment still faces two key challenges: (1) an inherent conflict between achieving high generation quality and ensuring low-latency inference, making it difficult to balance the two, and (2) insufficient interaction between user and item features in existing methods. To address these challenges, we propose a novel Personalized Semi-Autoregressive with online knowledge Distillation (PSAD) framework for reranking. In this framework, the teacher model adopts a semi-autoregressive generator to balance generation quality and efficiency, while its ranking knowledge is distilled online into a lightweight scoring network during joint training, enabling real-time and efficient inference. Furthermore, we propose a User Profile Network (UPN) that injects user intent and models interest dynamics, enabling deeper interactions between users and items. Extensive experiments conducted on three large-scale public datasets demonstrate that PSAD significantly outperforms state-of-the-art baselines in both ranking performance and inference efficiency.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Personalized Reranking on Ad](<https://www.sota2.com/research/sota/personalized-reranking-on-ad.md>): Personalized Reranking; AD; N@5: 70.38.

- [Personalized Reranking on PRM Public](<https://www.sota2.com/research/sota/personalized-reranking-on-prm-public.md>): Personalized Reranking; PRM Public; N@5: 0.2762.

- [Personalized Reranking on Avtio](<https://www.sota2.com/research/sota/personalized-reranking-on-avtio.md>): Personalized Reranking; Avtio; N@5: 74.27.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.07107>)

[PDF](<https://arxiv.org/pdf/2603.07107.pdf>)
