DeGRe: Dense-supervised Generative Reranking for Recommendation

• URL: http://arxiv.org/abs/2605.25749v1
• Date: Mon, 25 May 2026 12:00:42 GMT
• Title: DeGRe: Dense-supervised Generative Reranking for Recommendation
• Abstract summary: We propose DeGRe, a generative reranking framework that bridges the gap between offline exploration and online efficiency through dense supervision.<n>During training, we transform the step-wise value estimations from the evaluator into dense supervision signals and distill them into a lightweight Online Generator.<n>We have successfully deployed DeGRe on Taobao Flash Shopping, significantly improving online recommendations.
• Score: 22.41679588580571
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In multi-stage recommender systems, reranking optimizes overall utility by capturing intra-list contextual dependencies, yet its central challenge lies in exploring optimal sequences within an exponentially large permutation space. Recent studies have shifted towards end-to-end generative frameworks, which typically leverage list-wise rewards or preference alignment to guide generator training. However, these methods still face two critical issues. First is the heuristic label bias. Existing methods often construct training targets based on simple rules, such as promoting clicked items to the top, while ignoring causal dependencies within the list context. Second is the credit assignment problem. Sparse list-level posterior rewards fail to directly guide intermediate steps in sequence generation, leading to ambiguous optimization directions. To address these issues, we propose DeGRe (Dense-supervised Generative Reranking), a generative reranking framework that bridges the gap between offline exploration and online efficiency through dense supervision. The core of DeGRe lies in its offline-online decoupled design. During the offline phase, we introduce a Lookahead Evaluator based on cumulative regression, which leverages beam search to actively mine high-value lookahead sequences in the unexposed space. During training, we transform the step-wise value estimations from the evaluator into dense supervision signals and distill them into a lightweight Online Generator. This mechanism enables the generator to internalize lookahead planning capabilities, requiring only a single efficient greedy decoding pass during online inference to approximate the global optimum. Experiments demonstrate that DeGRe outperforms baseline models on public benchmarks and industrial datasets. We have successfully deployed DeGRe on Taobao Flash Shopping, significantly improving online recommendations.

Related papers

• REVES: REvision and VErification--Augmented Training for Test-Time Scaling [53.197756110943395]
  We propose a two-stage iterative framework that alternates between online data/prompt augmentation and policy optimization.<n>We observe gains of +6.5 points over the RL baseline and +4.0 points over standard multi-turn training.
  arXiv  Detail & Related papers  (2026-06-17T10:37:23Z)
• INFUSER: Influence-Guided Self-Evolution Improves Reasoning [54.101135873140066]
  We introduce an iterative co-training framework with two co-evolving roles.<n>A solver is trained with standard correctness rewards against the generator-provided answers.<n>An 8B INF co-evolving generator outperforms a frozen 32B thinking generator on math and coding.
  arXiv  Detail & Related papers  (2026-06-08T05:40:36Z)
• From Local Indices to Global Identifiers: Generative Reranking for Recommender Systems via Global Action Space [50.72071213515985]
  GloRank is a generative framework that shifts reranking from selecting local indices to generating global identifiers.<n>We show that GloRank consistently outperforms state-of-the-art baselines and achieves superior robustness in cold-start scenarios.
  arXiv  Detail & Related papers  (2026-04-28T06:57:00Z)
• RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time [51.256131853751754]
  We show that teaching reward models to produce explicit, multi-dimensional critiques transforms them from passive evaluators into active optimization tools.<n>We introduce Preference-Anchored Rationalization (PARROT), a principled framework that recovers high-quality rationales from readily available preference data.<n>The resulting model, RationalRewards (8B), achieves state-of-the-art preference prediction among open-source reward models.
  arXiv  Detail & Related papers  (2026-04-13T15:38:09Z)
• Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning [79.88942231770629]
  Reinforcement learning (RL) has become a central post-training tool for improving the reasoning abilities of large language models (LLMs)<n>We formalize rollout pipelines with unified notation and introduce Generate-Filter-Control-Replay (GFCR)<n>We synthesize methods spanning RL with verifiable rewards, process supervision, judge-based gating, guided and tree/segment rollouts, adaptive compute allocation, early-exit and partial rollouts, throughput optimization, and replay/recomposition for self-improvement.
  arXiv  Detail & Related papers  (2026-04-08T00:53:29Z)
• Next-Scale Generative Reranking: A Tree-based Generative Rerank Method at Meituan [19.27715432069165]
  We introduce a next-scale generator (NSG) that progressively expands a recommendation list from user interests in a coarse-to-fine manner.<n>NSGR has been successfully deployed on the Meituan food delivery platform.
  arXiv  Detail & Related papers  (2026-04-07T01:35:20Z)
• RankGR: Rank-Enhanced Generative Retrieval with Listwise Direct Preference Optimization in Recommendation [36.297513746770456]
  We propose RankGR, a Generative Retrieval method that incorporates listwise direct preference optimization for recommendation.<n>In IAP, we incorporate a novel listwise direct preference optimization strategy into GR, thus facilitating a more comprehensive understanding of the hierarchical user preferences.<n>We implement several practical improvements in training and deployment, ultimately achieving a real-time system capable of handling nearly ten thousand requests per second.
  arXiv  Detail & Related papers  (2026-02-09T12:13:43Z)
• SimGR: Escaping the Pitfalls of Generative Decoding in LLM-based Recommendation [68.00727783181289]
  A core objective in recommender systems is to accurately model the distribution of user preferences over items to enable personalized recommendations.<n>We observe that existing methods inevitably introduce systematic bias when estimating item-level preference distributions.<n>We propose textbfSimply textbfGenerative textbfRecommendation (textbfSimGR), a framework that directly models item-level preference distributions in a shared latent space.
  arXiv  Detail & Related papers  (2026-02-08T07:26:52Z)
• GReF: A Unified Generative Framework for Efficient Reranking via Ordered Multi-token Prediction [12.254397628788647]
  Reranking plays a crucial role in modeling intra-list correlations among items.<n>Recent research follows a two-stage (generator-evaluator) paradigm.<n>We propose a Unified Generative Efficient Reranking Framework (GReF) to address the two primary challenges.
  arXiv  Detail & Related papers  (2025-10-29T06:54:42Z)
• NLGR: Utilizing Neighbor Lists for Generative Rerank in Personalized Recommendation Systems [13.848284819312953]
  Neighbor Lists model for Generative Reranking aims to improve the performance of the generator in the space.<n>We propose a novel sampling-based non-autoregressive generation method, which allows the generator to jump flexibly from the current list to any neighbor list.<n>Experiments on public and industrial datasets validate NLGR's effectiveness and we have successfully deployed NLGR on the Meituan food delivery platform.
  arXiv  Detail & Related papers  (2025-02-10T02:06:17Z)
• Unsupervised Controllable Generation with Self-Training [90.04287577605723]
  controllable generation with GANs remains a challenging research problem. We propose an unsupervised framework to learn a distribution of latent codes that control the generator through self-training. Our framework exhibits better disentanglement compared to other variants such as the variational autoencoder.
  arXiv  Detail & Related papers  (2020-07-17T21:50:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.