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

arXiv: https://arxiv.org/abs/2603.07107 · HTML: https://mlsanity.com/paper/2603.07107/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Distillation for recommender systems, one of 12 directions in Knowledge distillation.
- Builds on 52 of its 65 references that are in the map.
- First posted on arXiv 7 Mar 2026.

## Placed in

- Knowledge distillation / [Distillation for recommender systems](https://mlsanity.com/distill/distillation-for-recommender-systems/)

## Builds on (most cited first, 30 of 52)

- [A Survey on Large Language Models for Recommendation](https://mlsanity.com/paper/2305.19860/) (2023)
- [Blockwise Parallel Decoding for Deep Autoregressive Models](https://mlsanity.com/paper/1811.03115/) (2018)
- [OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignment](https://mlsanity.com/paper/2502.18965/) (2025)
- [Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation](https://mlsanity.com/paper/2203.16487/) (2022)
- [Learning a Deep Listwise Context Model for Ranking Refinement](https://mlsanity.com/paper/1804.05936/) (2018)
- [Semi-Autoregressive Neural Machine Translation](https://mlsanity.com/paper/1808.08583/) (2018)
- [SetRank: Learning a Permutation-Invariant Ranking Model for Information Retrieval](https://mlsanity.com/paper/1912.05891/) (2019)
- [Seq2Slate: Re-ranking and Slate Optimization with RNNs](https://mlsanity.com/paper/1810.02019/) (2018)
- [MCNE: An End-to-End Framework for Learning Multiple Conditional Network Representations of Social Network](https://mlsanity.com/paper/1905.11013/) (2019)
- [Learning Groupwise Multivariate Scoring Functions Using Deep Neural Networks](https://mlsanity.com/paper/1811.04415/) (2018)
- [Real-time Short Video Recommendation on Mobile Devices](https://mlsanity.com/paper/2208.09577/) (2022)
- [Neural Re-ranking in Multi-stage Recommender Systems: A Review](https://mlsanity.com/paper/2202.06602/) (2022)
- [Generative Flow Network for Listwise Recommendation](https://mlsanity.com/paper/2306.02239/) (2023)
- [Discrete Conditional Diffusion for Reranking in Recommendation](https://mlsanity.com/paper/2308.06982/) (2023)
- [Enhancing Recommendation Diversity by Re-ranking with Large Language Models](https://mlsanity.com/paper/2401.11506/) (2024)
- [Dataset Regeneration for Sequential Recommendation](https://mlsanity.com/paper/2405.17795/) (2024)
- [RAPID: Efficient Retrieval-Augmented Long Text Generation with Writing Planning and Information Discovery](https://mlsanity.com/paper/2503.00751/) (2025)
- [Globally Optimized Mutual Influence Aware Ranking in E-Commerce Search](https://mlsanity.com/paper/1805.08524/) (2018)
- [Non-autoregressive Generative Models for Reranking Recommendation](https://mlsanity.com/paper/2402.06871/) (2024)
- [ChemEval: A Comprehensive Multi-Level Chemical Evaluation for Large Language Models](https://mlsanity.com/paper/2409.13989/) (2024)
- [Thought-Augmented Planning for LLM-Powered Interactive Recommender Agent](https://mlsanity.com/paper/2506.23485/) (2025)
- [Revisit Recommender System in the Permutation Prospective](https://mlsanity.com/paper/2102.12057/) (2021)
- [On component interactions in two-stage recommender systems](https://mlsanity.com/paper/2106.14979/) (2021)
- [GRN: Generative Rerank Network for Context-wise Recommendation](https://mlsanity.com/paper/2104.00860/) (2021)
- [Scaling New Frontiers: Insights into Large Recommendation Models](https://mlsanity.com/paper/2412.00714/) (2024)
- [TD3: Tucker Decomposition Based Dataset Distillation Method for Sequential Recommendation](https://mlsanity.com/paper/2502.02854/) (2025)
- [Generative Large Recommendation Models: Emerging Trends in LLMs for Recommendation](https://mlsanity.com/paper/2502.13783/) (2025)
- [Killing Two Birds with One Stone: Unifying Retrieval and Ranking with a Single Generative Recommendation Model](https://mlsanity.com/paper/2504.16454/) (2025)
- [PEAR: Personalized Re-ranking with Contextualized Transformer for Recommendation](https://mlsanity.com/paper/2203.12267/) (2022)
- [Breaking Determinism: Fuzzy Modeling of Sequential Recommendation Using Discrete State Space Diffusion Model](https://mlsanity.com/paper/2410.23994/) (2024)

## Built on by (most cited first, 3 of 3)

- [Learning from Emptiness: De-biasing Listwise Rerankers with Content-Agnostic Probability Calibration](https://mlsanity.com/paper/2604.10150/) (2026)
- [IE as Cache: Information Extraction Enhanced Agentic Reasoning](https://mlsanity.com/paper/2604.14930/) (2026)
- [Rethinking the Necessity of Adaptive Retrieval-Augmented Generation through the Lens of Adaptive Listwise Ranking](https://mlsanity.com/paper/2604.15621/) (2026)

## Abstract (arXiv)

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.